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

    Neuronpedia

    INDEX
    Explanations

    Legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
     Tampa
    -0.07
    领袖
    -0.07
     tossed
    -0.07
     Eduardo
    -0.06
     zs
    -0.06
     Soil
    -0.06
    שקע
    -0.06
    🍞
    -0.06
    蹅
    -0.06
    POSITIVE LOGITS
     scripted
    0.07
    CREMENT
    0.07
    ��이
    0.07
    .IDENTITY
    0.07
     reson
    0.07
    蜗
    0.07
    per
    0.07
    ali
    0.06
     documents
    0.06
    褥
    0.06
    Act Density 0.126%

    No Known Activations