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

    Neuronpedia

    INDEX
    Explanations

    definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     STOP
    -0.07
    бол
    -0.07
    нения
    -0.07
    _copy
    -0.07
    Message
    -0.07
     salvar
    -0.06
    灭
    -0.06
    没
    -0.06
    _exists
    -0.06
    .toBe
    -0.06
    POSITIVE LOGITS
     tact
    0.06
     Accent
    0.06
    _extractor
    0.06
     makeStyles
    0.06
    law
    0.06
    (sess
    0.06
    (cursor
    0.06
    acciones
    0.05
    ],&
    0.05
    _parsed
    0.05
    Act Density 0.009%

    No Known Activations