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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     raped
    -0.07
     Pivot
    -0.07
    mse
    -0.06
     stricter
    -0.06
    _One
    -0.06
     qualifier
    -0.06
    وتر
    -0.06
    袋
    -0.06
     glac
    -0.06
     dán
    -0.06
    POSITIVE LOGITS
    /";↵
    0.07
     طبی
    0.07
    """),↵
    0.06
    ambi
    0.06
    /how
    0.06
    .scope
    0.06
    raries
    0.06
     investigating
    0.06
    _transition
    0.06
     sammen
    0.06
    Act Density 0.003%

    No Known Activations