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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases indicating conditions or comparisons

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

    prepositional phrases describing relations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nere
    -0.41
     DEV
    -0.41
    nut
    -0.40
    Zul
    -0.36
    Dev
    -0.36
     affari
    -0.35
    < 
    -0.34
    RSM
    -0.34
    thro
    -0.34
     tovább
    -0.32
    POSITIVE LOGITS
    PMailer
    0.68
    évaluateur
    0.66
    RTEE
    0.61
    StoryboardSegue
    0.60
    ContentLoaded
    0.58
     חיצוניים
    0.52
     للاسماء
    0.50
    verwijspagina
    0.50
    gerufen
    0.50
    fromnode
    0.49
    Act Density 0.373%

    No Known Activations