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
     misunderstood
    -0.06
    uniacid
    -0.06
     diss
    -0.06
     Kunst
    -0.06
    Foo
    -0.06
     quoted
    -0.05
     Rahman
    -0.05
     Fir
    -0.05
    .getTransaction
    -0.05
    .us
    -0.05
    POSITIVE LOGITS
    Ã
    0.08
     बन
    0.08
    。↵↵↵↵↵↵
    0.07
    ヴァ
    0.06
    clusions
    0.06
    Pixel
    0.06
    Steve
    0.06
     Ney
    0.06
    orial
    0.06
    搬
    0.06
    Act Density 0.000%

    No Known Activations