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

    Neuronpedia

    INDEX
    Explanations

    instances of specific items and their characteristics within various contexts

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

    possessive or contraction endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.43
     karşılaş
    -0.39
     picioare
    -0.39
     ziyaret
    -0.38
    NameInMap
    -0.36
    withIdentifier
    -0.36
     klikken
    -0.36
     secretario
    -0.35
     estacionamento
    -0.35
     durchschnitt
    -0.35
    POSITIVE LOGITS
     esternos
    0.61
     للمعارف
    0.52
    pædia
    0.52
     سكانية
    0.49
    斗
    0.48
    domada
    0.46
    ftagPool
    0.46
    thday
    0.45
    EndGlobal
    0.45
     balan
    0.45
    Act Density 0.161%

    No Known Activations