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

    Neuronpedia

    INDEX
    Explanations

    Data tables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    We're
    -0.07
    aliro
    -0.07
     speak
    -0.07
     பேச
    -0.07
     continuer
    -0.07
    _continue
    -0.07
    Doors
    -0.07
    (inner
    -0.07
     बोल
    -0.07
     inner
    -0.07
    POSITIVE LOGITS
     Powell
    0.09
     profitability
    0.08
     порядок
    0.08
     transparente
    0.08
     negativity
    0.08
     tankou
    0.07
    _EXIST
    0.07
     transparency
    0.07
     отс
    0.07
     Parker
    0.07
    Act Density 0.018%

    No Known Activations