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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ub
    -0.07
     seaside
    -0.07
     Arap
    -0.07
    orů
    -0.07
     Cs
    -0.06
     Garland
    -0.06
    _Pods
    -0.06
     discontin
    -0.06
     divisive
    -0.06
    snake
    -0.06
    POSITIVE LOGITS
     IIC
    0.06
    Inter
    0.06
     humanity
    0.06
     Cas
    0.06
     cada
    0.06
    TimeZone
    0.06
    ()==
    0.06
    lyphicon
    0.06
     Coming
    0.06
    .compare
    0.06
    Act Density 0.049%

    No Known Activations