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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elapsed
    -0.07
    計算
    -0.07
     alliance
    -0.06
    .emit
    -0.06
     swore
    -0.06
    ematics
    -0.06
    /english
    -0.05
    charset
    -0.05
    _death
    -0.05
     scope
    -0.05
    POSITIVE LOGITS
    _answer
    0.07
     °
    0.07
    -align
    0.07
     Plex
    0.07
    .ButterKnife
    0.07
     NRA
    0.07
     vzděl
    0.07
    ucc
    0.06
    Mov
    0.06
    TZ
    0.06
    Act Density 0.004%

    No Known Activations