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

    Neuronpedia

    INDEX
    Explanations

    Medical analysis or diagnosis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     até
    -0.07
     Contribution
    -0.07
    .Static
    -0.07
     explan
    -0.06
     traced
    -0.06
     Lore
    -0.06
    Rank
    -0.06
    승
    -0.06
    _TRACK
    -0.06
     Ook
    -0.06
    POSITIVE LOGITS
    ma
    0.07
    (secret
    0.06
     pokemon
    0.06
     spel
    0.06
     chlap
    0.06
     Chew
    0.06
     Bras
    0.06
    juries
    0.06
     culpa
    0.06
    атег
    0.06
    Act Density 0.027%

    No Known Activations