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

    Neuronpedia

    INDEX
    Explanations

    /pm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Reverse
    -0.07
     ร
    -0.07
     peny
    -0.06
    	eval
    -0.06
    =n
    -0.06
    とする
    -0.06
    	R
    -0.06
    ้
    -0.06
     bahsed
    -0.06
    ARS
    -0.06
    POSITIVE LOGITS
    reduce
    0.07
    %"↵
    0.06
     '}↵
    0.06
    今年
    0.06
    �始化
    0.06
     postings
    0.06
     "+↵
    0.06
    cação
    0.06
    .exception
    0.06
    ENTE
    0.06
    Act Density 0.017%

    No Known Activations