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

    Neuronpedia

    INDEX
    Explanations

    references to various models used in scientific studies

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

    model parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awtextra
    -0.44
    PhysRev
    -0.40
     convertView
    -0.39
     Paglinawan
    -0.36
    MergeFrom
    -0.36
    MLLoader
    -0.36
     useAppContext
    -0.36
     Gain
    -0.34
    FormBuilder
    -0.34
    enumi
    -0.34
    POSITIVE LOGITS
     Anſ
    0.54
    يميديا
    0.52
    wiſe
    0.52
     fernández
    0.50
     sandero
    0.49
     estadounid
    0.48
    igneur
    0.48
     kapturem
    0.48
    demment
    0.48
     capot
    0.47
    Act Density 0.037%

    No Known Activations