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

    Neuronpedia

    INDEX
    Explanations

    relationships and conditions expressed in mathematical terms

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

    zero corresponds to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Viited
    -0.45
    OrFail
    -0.43
     guapos
    -0.42
    (")");
    -0.41
     frecuentes
    -0.39
     prisa
    -0.39
    orited
    -0.38
    AddRange
    -0.38
    arXiv
    -0.38
     فريبيس
    -0.37
    POSITIVE LOGITS
     Zero
    0.78
     zero
    0.78
    Zero
    0.71
     ZERO
    0.70
    zero
    0.68
    ZERO
    0.61
     zéro
    0.60
    zeros
    0.59
     zeros
    0.58
    IntoConstraints
    0.53
    Act Density 0.314%

    No Known Activations