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

    Neuronpedia

    INDEX
    Explanations

    code and files

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jes
    -0.07
     thiệu
    -0.07
    	string
    -0.07
     odstran
    -0.06
    "];↵
    -0.06
     losses
    -0.06
     واقعی
    -0.06
    QString
    -0.06
    _ALLOWED
    -0.06
    AKE
    -0.06
    POSITIVE LOGITS
     frac
    0.07
    kır
    0.07
    폴
    0.06
     ihtiy
    0.06
    か
    0.06
     sr
    0.06
     λέ
    0.06
     Tv
    0.06
     ansch
    0.06
    -facebook
    0.06
    Act Density 0.078%

    No Known Activations