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

    Neuronpedia

    INDEX
    Explanations

    math calculations and proofs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     haw
    -0.09
     অত্য
    -0.08
    CORE
    -0.08
    <|endoftext|>
    -0.07
     e
    -0.07
     अत्य
    -0.07
    dum
    -0.07
     לב
    -0.07
     du
    -0.07
    يني
    -0.07
    POSITIVE LOGITS
     опять
    0.09
     again
    0.09
     следующ
    0.09
    inski
    0.08
    -cycle
    0.08
     Again
    0.08
     снова
    0.08
     следующий
    0.08
     下一
    0.08
     potenci
    0.08
    Act Density 0.018%

    No Known Activations