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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     %=
    -0.08
    育
    -0.07
    垯
    -0.07
     orgasm
    -0.07
     <=>
    -0.07
    Coding
    -0.07
     dames
    -0.07
    更是
    -0.07
    Saved
    -0.06
    ая
    -0.06
    POSITIVE LOGITS
    .HOUR
    0.08
     Battle
    0.08
    _metric
    0.07
    _PART
    0.07
    _choice
    0.07
    (lat
    0.07
    (price
    0.07
    COMPLETE
    0.07
    (PORT
    0.07
    (loc
    0.07
    Act Density 0.027%

    No Known Activations