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

    Neuronpedia

    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _df
    -0.07
    \ActiveForm
    -0.06
    gradation
    -0.06
     polygon
    -0.06
    양
    -0.06
    .SYSTEM
    -0.06
     automation
    -0.06
     vegan
    -0.06
     orchestrated
    -0.06
     โดย
    -0.06
    POSITIVE LOGITS
    ательно
    0.06
    llll
    0.06
     ali
    0.06
     riches
    0.06
    RH
    0.06
     wish
    0.06
    178
    0.06
    197
    0.06
    (cal
    0.05
     Head
    0.05
    Act Density 0.024%

    No Known Activations