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

    Neuronpedia

    INDEX
    Explanations

    code/math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inee
    -0.07
    azing
    -0.07
    mie
    -0.06
     ως
    -0.06
     TOD
    -0.06
     cupboard
    -0.06
    rob
    -0.06
    .ob
    -0.06
     qty
    -0.06
    бо
    -0.06
    POSITIVE LOGITS
    义
    0.07
    marvin
    0.06
    มต
    0.06
    Neil
    0.06
    ड़क
    0.06
     elders
    0.06
    義
    0.06
    ุตสาห
    0.06
    Apis
    0.06
     usize
    0.06
    Act Density 0.000%

    No Known Activations