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

    Neuronpedia

    INDEX
    Explanations

    Math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    estr
    -0.07
     Kür
    -0.07
    -on
    -0.07
     minor
    -0.07
    .refs
    -0.06
    -needed
    -0.06
     Borough
    -0.06
    \Image
    -0.06
    IB
    -0.06
     Bott
    -0.06
    POSITIVE LOGITS
    cal
    0.09
    Transaction
    0.07
    Camp
    0.07
     deja
    0.07
    _sql
    0.07
     시스템
    0.07
    acterial
    0.07
     suits
    0.07
     放
    0.07
    کات
    0.06
    Act Density 0.003%

    No Known Activations