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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     characteristic
    -0.07
    County
    -0.07
     merit
    -0.07
    Box
    -0.06
     width
    -0.06
     satış
    -0.06
     Radio
    -0.06
    _ne
    -0.06
    Population
    -0.06
     thermal
    -0.06
    POSITIVE LOGITS
     женщин
    0.07
    ":[
    0.06
    魔法
    0.06
     منط
    0.06
    ไม
    0.06
     Found
    0.06
     мої
    0.06
     आपक
    0.06
    σμ
    0.06
    (json
    0.06
    Act Density 0.005%

    No Known Activations