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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    JP
    -0.07
     reused
    -0.06
    他
    -0.06
    jay
    -0.06
     Spread
    -0.06
     Slave
    -0.06
     corpses
    -0.06
    سان
    -0.06
     toler
    -0.06
    번호
    -0.06
    POSITIVE LOGITS
     음
    0.06
     espec
    0.06
     thunder
    0.06
     Scouts
    0.06
     쿠
    0.06
    _subplot
    0.06
     invokevirtual
    0.06
    ificial
    0.06
    
    0.06
     بك
    0.06
    Act Density 0.019%

    No Known Activations