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

    Neuronpedia

    INDEX
    Explanations

    compact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -term
    -0.07
    CHANNEL
    -0.07
    rrha
    -0.07
    ��
    -0.06
    ccoli
    -0.06
     output
    -0.06
     đội
    -0.06
    ===
    -0.06
     seper
    -0.06
     mph
    -0.06
    POSITIVE LOGITS
    nowled
    0.06
     Ná
    0.06
    din
    0.06
    _BY
    0.06
    antics
    0.06
    .neo
    0.06
    ポート
    0.06
    ifications
    0.06
    olutely
    0.06
    WARDS
    0.06
    Act Density 0.001%

    No Known Activations