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

    Neuronpedia

    INDEX
    Explanations

    terms related to influence and change

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

    how things change and influence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.61
    ंदीखरीदारी
    -0.57
    enumii
    -0.54
    RegressionTest
    -0.51
     שוליים
    -0.50
    localctx
    -0.49
    يميديا
    -0.49
    ConstraintMaker
    -0.49
    addPreferredGap
    -0.48
     unil
    -0.48
    POSITIVE LOGITS
     motocicletas
    0.42
    How
    0.41
     hogyan
    0.40
     How
    0.40
     jspb
    0.39
     how
    0.39
     nyní
    0.36
     embarazadas
    0.36
    aimana
    0.35
     Pourquoi
    0.34
    Act Density 0.054%

    No Known Activations