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
    öh
    -0.08
     freder
    -0.07
    .Sm
    -0.06
    869
    -0.06
    III
    -0.06
    667
    -0.06
    Extern
    -0.06
    inth
    -0.06
    ’den
    -0.06
    ンド
    -0.06
    POSITIVE LOGITS
    ¿
    0.09
     Λ
    0.07
    toMatchSnapshot
    0.07
     justice
    0.07
    ;|
    0.07
    raid
    0.07
    rollers
    0.07
    атели
    0.06
    (px
    0.06
     defeating
    0.06
    Act Density 0.003%

    No Known Activations