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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     painful
    -0.07
     Capitals
    -0.07
    易
    -0.07
    民族文化
    -0.07
    Iterable
    -0.07
    染
    -0.07
     כאמ
    -0.07
     inverse
    -0.07
    ונ
    -0.07
    apache
    -0.06
    POSITIVE LOGITS
     говор
    0.08
    🈯
    0.07
     construed
    0.07
     sagte
    0.07
     kitty
    0.07
     introduce
    0.07
    Sigma
    0.07
    מעניק
    0.07
    >tagger
    0.07
     onUpdate
    0.07
    Act Density 0.100%

    No Known Activations