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

    Neuronpedia

    INDEX
    Explanations

    geometric

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dfd
    -0.07
    xEF
    -0.06
     выбра
    -0.06
     erotik
    -0.06
    bla
    -0.06
    111
    -0.06
    .assets
    -0.06
     kanı
    -0.06
    pus
    -0.06
    `;
    -0.06
    POSITIVE LOGITS
     geometric
    0.16
    ometric
    0.10
    kwargs
    0.07
     Comm
    0.07
     більш
    0.07
     pharmac
    0.07
    geom
    0.07
     Est
    0.07
    resent
    0.07
     tokenizer
    0.07
    Act Density 0.002%

    No Known Activations