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

    Neuronpedia

    INDEX
    Explanations

    See

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Division
    -0.07
    523
    -0.06
    콜걸
    -0.06
    573
    -0.06
     disp
    -0.06
    ріб
    -0.06
     equ
    -0.06
    FAIL
    -0.06
     airing
    -0.06
    _Space
    -0.06
    POSITIVE LOGITS
    .side
    0.07
     ms
    0.06
     rsa
    0.06
    ='"
    0.06
     chrom
    0.06
     mohla
    0.06
    {(
    0.06
     korum
    0.06
    .nama
    0.06
    (contract
    0.06
    Act Density 0.002%

    No Known Activations