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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tryside
    -0.07
     Venture
    -0.07
     horrible
    -0.06
    _int
    -0.06
     Bros
    -0.06
     Kot
    -0.06
    esan
    -0.06
    uffle
    -0.06
     Lan
    -0.06
    CLE
    -0.06
    POSITIVE LOGITS
    :'+
    0.07
    सम
    0.07
    .'.$
    0.07
    ;
↵
    0.06
     enim
    0.06
     scav
    0.06
    τές
    0.06
     kısm
    0.06
    _IL
    0.06
    inkel
    0.06
    Act Density 0.042%

    No Known Activations