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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lanc
    -0.07
     mpg
    -0.07
     или
    -0.06
     nouns
    -0.06
    Those
    -0.06
     Vance
    -0.06
     Orch
    -0.06
     及
    -0.06
     cheer
    -0.06
     stockings
    -0.06
    POSITIVE LOGITS
     enticing
    0.06
     Σ
    0.06
     yatır
    0.06
    .ipv
    0.06
     λέ
    0.06
    ン
    0.06
    fecha
    0.06
    isz
    0.06
    .Mult
    0.06
    _PW
    0.06
    Act Density 0.077%

    No Known Activations