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

    Neuronpedia

    INDEX
    Explanations

    non-English

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     לקחת
    -0.07
     insufficient
    -0.06
     dirig
    -0.06
    RefPtr
    -0.06
     inconsistency
    -0.06
     hé
    -0.06
     conflict
    -0.06
    TF
    -0.06
     tendrá
    -0.06
     Nazi
    -0.06
    POSITIVE LOGITS
    ret
    0.07
     Shen
    0.07
    的模样
    0.07
    青睐
    0.07
    ount
    0.07
    Palette
    0.07
    株洲
    0.07
     LAT
    0.07
    关注
    0.07
    头条
    0.07
    Act Density 0.060%

    No Known Activations