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

    Neuronpedia

    INDEX
    Explanations

    problem-solving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .other
    -0.08
    ました
    -0.06
    _dicts
    -0.06
    queueReusableCell
    -0.06
    _integration
    -0.06
     Вели
    -0.06
     κυ
    -0.06
    autiful
    -0.06
    Endpoints
    -0.06
     якості
    -0.06
    POSITIVE LOGITS
    roduce
    0.07
    สำน
    0.06
     Bend
    0.06
    irement
    0.06
     Margin
    0.06
     Dat
    0.06
    _stderr
    0.06
    ành
    0.06
    _ET
    0.06
     Ment
    0.06
    Act Density 0.281%

    No Known Activations