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

    Neuronpedia

    INDEX
    Explanations

    convention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     سری
    -0.07
     Measures
    -0.07
     meer
    -0.06
     Features
    -0.06
     bizi
    -0.06
     deployments
    -0.06
    盟
    -0.06
    Seen
    -0.06
    _alert
    -0.06
     JV
    -0.06
    POSITIVE LOGITS
     relics
    0.06
    .interpolate
    0.06
    Nich
    0.06
    cran
    0.06
    National
    0.06
     National
    0.06
     Carrier
    0.06
    忠
    0.06
    /cache
    0.06
     Phoenix
    0.06
    Act Density 0.002%

    No Known Activations