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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Đây
    -0.07
    crc
    -0.07
     randomNumber
    -0.07
     {"
    -0.06
    -ser
    -0.06
    .*;
↵
    -0.06
    Das
    -0.06
     ])->
    -0.06
    دری
    -0.06
    三个
    -0.06
    POSITIVE LOGITS
     Potential
    0.07
     Goa
    0.07
    イク
    0.07
    +B
    0.06
    IFA
    0.06
     ê
    0.06
    .getClassName
    0.06
     potential
    0.06
    ах
    0.06
    orta
    0.06
    Act Density 0.010%

    No Known Activations