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

    Neuronpedia

    INDEX
    Explanations

    technical and scientific texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    半夜
    -0.07
    pmat
    -0.07
     lick
    -0.07
    _TC
    -0.07
     warranty
    -0.07
    cone
    -0.07
     самостоятельно
    -0.07
    _DST
    -0.07
     nehmen
    -0.07
     deletes
    -0.07
    POSITIVE LOGITS
     Pager
    0.07
    波动
    0.06
    /vnd
    0.06
    @RestController
    0.06
    挥
    0.06
     Hoàng
    0.06
    身影
    0.06
    _pass
    0.06
    _turn
    0.06
    Quarter
    0.06
    Act Density 0.092%

    No Known Activations