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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <h
    -0.07
    Closed
    -0.07
    ii
    -0.07
    %">
    -0.06
     petitions
    -0.06
    -0.06
     bounded
    -0.06
    calls
    -0.06
    >(),
    -0.06
     필요한
    -0.06
    POSITIVE LOGITS
    -theme
    0.06
     mädchen
    0.06
     alex
    0.06
    _surf
    0.06
    WithType
    0.06
     пояс
    0.06
     Norse
    0.06
    Align
    0.06
    ินด
    0.06
     mů
    0.05
    Act Density 0.019%

    No Known Activations