Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that involve unusual actions or physical abilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following prepositions/punctuation

    np_acts-logits-general · gemini-2.0-flash

    concrete nouns followed by descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conmigo
    -0.48
     disfrutando
    -0.38
     Umgang
    -0.38
     cordones
    -0.36
     creciendo
    -0.36
     conoce
    -0.36
     consideración
    -0.36
     sekitarnya
    -0.35
     kesim
    -0.35
     rapides
    -0.34
    POSITIVE LOGITS
    Autoritní
    0.90
     Normdatei
    0.82
     Photocase
    0.82
    səhifə
    0.70
     CanadaChoose
    0.69
     kasarigan
    0.67
     autorytatywna
    0.66
    ConstraintMaker
    0.66
    AndroidJUnit
    0.66
    stateProvider
    0.63
    Act Density 0.527%

    No Known Activations