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

    Neuronpedia

    INDEX
    Explanations

    expressions of desire or intent

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

    if you want

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Izvori
    -0.32
    addPreferredGap
    -0.31
     surla
    -0.31
     préféré
    -0.30
     préf
    -0.29
     compositeur
    -0.29
     StringField
    -0.29
    viembre
    -0.28
    volmente
    -0.28
    ském
    -0.27
    POSITIVE LOGITS
    endcsname
    0.63
    rungsseite
    0.63
    ItemBackground
    0.60
    #
    0.60
    hoeddwyd
    0.60
    CloseOperation
    0.59
    fromnode
    0.58
    RTHOOK
    0.56
    neté
    0.56
    NameInMap
    0.56
    Act Density 0.026%

    No Known Activations