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

    Neuronpedia

    INDEX
    Explanations

    Morrison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     belief
    -0.08
     متفاوت
    -0.07
     battlefield
    -0.07
    าด
    -0.06
    Phone
    -0.06
     lou
    -0.06
    来了
    -0.06
    热
    -0.06
     Loads
    -0.06
    896
    -0.06
    POSITIVE LOGITS
     plastic
    0.07
     Morrison
    0.07
    (join
    0.07
    _ev
    0.06
     commuters
    0.06
    .GraphicsUnit
    0.06
    dıktan
    0.06
    (Qt
    0.06
     Fitzgerald
    0.06
    (copy
    0.06
    Act Density 0.002%

    No Known Activations