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

    Neuronpedia

    INDEX
    Explanations

    example

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .threshold
    -0.07
     компании
    -0.06
    .subtitle
    -0.06
    盟
    -0.06
    식
    -0.06
    .DotNetBar
    -0.06
    TB
    -0.06
    .contrib
    -0.06
    .Rows
    -0.06
     должна
    -0.06
    POSITIVE LOGITS
    scar
    0.06
     denial
    0.06
    ंट
    0.06
    ng
    0.06
    Edward
    0.06
     Hitler
    0.06
    quent
    0.06
    IDDEN
    0.06
    CEPT
    0.06
    斷
    0.06
    Act Density 0.006%

    No Known Activations