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

    Neuronpedia

    INDEX
    Explanations

    An

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LOGGER
    -0.07
    emperature
    -0.06
     fabricated
    -0.06
    辅
    -0.06
    ãi
    -0.06
     //<
    -0.06
     courage
    -0.06
     startled
    -0.06
     detailed
    -0.06
    (tok
    -0.06
    POSITIVE LOGITS
    онт
    0.07
    =__
    0.07
    ONT
    0.07
    .instant
    0.06
     otherButtonTitles
    0.06
    _pc
    0.06
     동일
    0.06
    _SELECTED
    0.06
     Vet
    0.06
     mdl
    0.06
    Act Density 0.006%

    No Known Activations