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

    Neuronpedia

    INDEX
    Explanations

    semicolon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sweat
    -0.07
    'ı
    -0.07
    ienia
    -0.07
    qb
    -0.07
    obuf
    -0.06
    律
    -0.06
    vae
    -0.06
    -_
    -0.06
    struct
    -0.06
     coward
    -0.06
    POSITIVE LOGITS
     actress
    0.07
     subjective
    0.07
    );
    0.07
    ;
    0.07
     fantastic
    0.07
    álním
    0.07
    ippets
    0.06
    不到
    0.06
    -chevron
    0.06
    Metadata
    0.06
    Act Density 0.029%

    No Known Activations