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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .mit
    -0.07
     Luxury
    -0.06
     incididunt
    -0.06
     lidi
    -0.06
    412
    -0.06
     Erotic
    -0.06
    .getActivity
    -0.06
    احل
    -0.06
    (tile
    -0.06
     Naturally
    -0.06
    POSITIVE LOGITS
     прор
    0.07
     churn
    0.06
    ीं।
    0.06
    -open
    0.06
    unded
    0.06
     traged
    0.06
     โ
    0.06
    vant
    0.06
    Initializer
    0.06
    _At
    0.06
    Act Density 0.003%

    No Known Activations