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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Conexion
    -0.08
     Viện
    -0.07
    椋
    -0.07
     inclusion
    -0.07
     Feed
    -0.07
    _excel
    -0.07
    吸入
    -0.07
    .daily
    -0.07
    ListOf
    -0.07
     Fern
    -0.07
    POSITIVE LOGITS
    ipi
    0.08
    nten
    0.07
     probe
    0.06
    ('$
    0.06
    -spot
    0.06
     Rob
    0.06
     gigs
    0.06
    Finally
    0.06
     metal
    0.06
    语法
    0.06
    Act Density 0.002%

    No Known Activations