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

    Neuronpedia

    INDEX
    Explanations

    while

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    הוצאת
    -0.08
    体制改革
    -0.07
    (Connection
    -0.07
    꾹
    -0.07
    _FL
    -0.07
    トラブル
    -0.07
     Reform
    -0.07
    疁
    -0.06
    Feedback
    -0.06
    .MM
    -0.06
    POSITIVE LOGITS
    .nan
    0.07
    DEV
    0.07
    type
    0.07
     ول
    0.07
     black
    0.07
     sil
    0.06
    铁
    0.06
     vert
    0.06
    heatmap
    0.06
    _GLOBAL
    0.06
    Act Density 0.008%

    No Known Activations