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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     getS
    -0.07
     оскільки
    -0.06
     Lambert
    -0.06
     розташ
    -0.06
    ")]
    -0.06
     hintText
    -0.06
     Faker
    -0.06
    .k
    -0.06
    inspect
    -0.06
     س
    -0.06
    POSITIVE LOGITS
    ewhat
    0.06
    ได
    0.06
    ':
↵
    0.06
    ！↵↵
    0.06
    -к
    0.06
    �单
    0.06
    跳
    0.06
    software
    0.06
    orney
    0.06
    _velocity
    0.06
    Act Density 0.044%

    No Known Activations