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

    Neuronpedia

    INDEX
    Explanations

    constitution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kidd
    -0.08
    addOn
    -0.07
     peaked
    -0.07
     nominations
    -0.07
     italiano
    -0.06
    گاه
    -0.06
     computation
    -0.06
     生命周期
    -0.06
    Cake
    -0.06
     kendisini
    -0.06
    POSITIVE LOGITS
    ỗng
    0.07
    _MIN
    0.06
     bel
    0.06
    esan
    0.06
    邮
    0.06
    ourage
    0.06
     Specify
    0.06
     fret
    0.06
    Notifications
    0.06
    .slim
    0.05
    Act Density 0.004%

    No Known Activations