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

    Neuronpedia

    INDEX
    Explanations

    advice-giving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (mapping
    -0.07
    (Convert
    -0.07
    .BorderSize
    -0.07
    iy
    -0.06
    value
    -0.06
    _leave
    -0.06
    оте
    -0.06
    {↵↵
    -0.06
    ễ
    -0.06
    iv
    -0.06
    POSITIVE LOGITS
    stroy
    0.06
    strain
    0.06
    NameValuePair
    0.06
     cleanup
    0.06
    dict
    0.06
    駆
    0.06
    uffer
    0.06
     بازیگر
    0.06
     joven
    0.06
    γω
    0.05
    Act Density 0.155%

    No Known Activations