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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     closely
    -0.07
    (op
    -0.07
     اين
    -0.06
    ньо
    -0.06
    ombok
    -0.06
    циях
    -0.06
     daylight
    -0.06
    .SelectedItems
    -0.06
     fraternity
    -0.06
    _Node
    -0.06
    POSITIVE LOGITS
    (IConfiguration
    0.07
     gul
    0.06
    Listening
    0.06
    خصوص
    0.06
    ="/
    0.06
    innacle
    0.06
    -best
    0.06
     ah
    0.06
    。</
    0.06
    جموع
    0.06
    Act Density 0.002%

    No Known Activations