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

    Neuronpedia

    INDEX
    Explanations

    URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    17
    -0.07
     PERFORMANCE
    -0.07
    Account
    -0.06
    هار
    -0.06
    阿
    -0.06
     tax
    -0.06
    .expand
    -0.06
     BLOCK
    -0.06
    embro
    -0.06
    $output
    -0.06
    POSITIVE LOGITS
     Candidates
    0.07
    orses
    0.07
    ,:),
    0.06
     (;
    0.06
     Beverage
    0.06
     більше
    0.06
    (OpCodes
    0.06
     dfs
    0.06
     тен
    0.06
     виб
    0.06
    Act Density 0.009%

    No Known Activations