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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _columns
    -0.07
    _GENERAL
    -0.07
    .student
    -0.07
    ogui
    -0.07
    ทอง
    -0.07
     QUESTION
    -0.07
    混
    -0.07
     phases
    -0.06
    費
    -0.06
     ترتیب
    -0.06
    POSITIVE LOGITS
     A
    0.07
    adní
    0.07
    -watch
    0.06
     detainees
    0.06
     stagn
    0.06
     creamy
    0.06
     bởi
    0.06
    اون
    0.06
    Want
    0.06
    Scaling
    0.06
    Act Density 0.029%

    No Known Activations