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

    Neuronpedia

    INDEX
    Explanations

    Changes compared to the past

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dozens
    -0.07
    ливі
    -0.07
     inspectors
    -0.07
    Hash
    -0.06
     Lambert
    -0.06
    bigint
    -0.06
     VARCHAR
    -0.06
     sayıda
    -0.06
     lé
    -0.06
     Holder
    -0.06
    POSITIVE LOGITS
     geological
    0.07
    uliar
    0.06
    ANO
    0.06
    ++){↵
    0.06
    caling
    0.06
    _REG
    0.06
     coarse
    0.06
     "./
    0.06
    _ERRORS
    0.06
    (real
    0.06
    Act Density 0.217%

    No Known Activations