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

    Neuronpedia

    INDEX
    Explanations

    references to supplementary materials and additional files in a document

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

    "Additional file"

    np_acts-logits-general · gemini-2.0-flash

    supplementary file references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ligators
    -0.69
     MainAxisSize
    -0.55
     BoxFit
    -0.54
     Авто
    -0.52
     виправивши
    -0.51
    ộn
    -0.51
    CppMethod
    -0.51
    õi
    -0.51
     авто
    -0.50
    ווה
    -0.50
    POSITIVE LOGITS
     bike
    0.95
     Bike
    0.88
     Cycling
    0.85
     cycling
    0.85
     bicycle
    0.84
    Bike
    0.82
     cyclist
    0.79
     vélo
    0.79
     bicycles
    0.78
     cyclists
    0.77
    Act Density 0.685%

    No Known Activations