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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     어떻게
    -0.07
    �게
    -0.07
    .memo
    -0.07
    仕
    -0.06
    ndef
    -0.06
    oid
    -0.06
     علاوه
    -0.06
    180
    -0.06
    							↵
    -0.06
     около
    -0.06
    POSITIVE LOGITS
     获取
    0.06
    =[↵
    0.06
    ，然后
    0.06
    iedy
    0.06
    ...)
    0.06
     bw
    0.06
     blames
    0.06
     rentals
    0.06
     Arabian
    0.06
     personn
    0.06
    Act Density 0.003%

    No Known Activations