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

    Neuronpedia

    INDEX
    Explanations

    non-English

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     D
    -0.06
    бач
    -0.06
    -off
    -0.06
    ixmap
    -0.06
     backbone
    -0.06
    URAL
    -0.06
    zp
    -0.06
     Achievement
    -0.06
     detach
    -0.06
     SCAN
    -0.06
    POSITIVE LOGITS
    (second
    0.06
    /uploads
    0.06
    В
    0.06
     게시
    0.06
     Nairobi
    0.06
    キング
    0.06
    arası
    0.06
     Croatia
    0.06
    Assembly
    0.06
    _logic
    0.06
    Act Density 0.101%

    No Known Activations