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

    Neuronpedia

    INDEX
    Explanations

    software code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    upport
    -0.08
     можете
    -0.06
     Она
    -0.06
     ga
    -0.06
    읊
    -0.06
    놈
    -0.06
    lda
    -0.06
    ова
    -0.06
    أسماء
    -0.06
     sourcing
    -0.06
    POSITIVE LOGITS
     implants
    0.08
     Kardashian
    0.07
     physics
    0.07
     recruiters
    0.07
    him
    0.07
    .scalatest
    0.07
     interactions
    0.07
    );↵↵↵↵↵
    0.07
    faq
    0.07
     fatalities
    0.07
    Act Density 0.008%

    No Known Activations