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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    误
    -0.06
    vious
    -0.06
    .rx
    -0.06
    زش
    -0.06
    И
    -0.06
    叫
    -0.06
    贸
    -0.06
     premiered
    -0.06
     겨
    -0.06
    kanı
    -0.06
    POSITIVE LOGITS
     institutes
    0.07
     стану
    0.07
     rooft
    0.06
     quelques
    0.06
    镇
    0.06
    ［
    0.06
    (store
    0.06
     normalization
    0.06
     سان
    0.06
     targets
    0.06
    Act Density 0.310%

    No Known Activations