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

    Neuronpedia

    INDEX
    Explanations

    scams and false pretenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .the
    -0.07
    hev
    -0.07
     Mentor
    -0.06
    伏
    -0.06
    正
    -0.06
    .Util
    -0.06
    .Strings
    -0.06
    okus
    -0.06
    fst
    -0.06
    .Mapping
    -0.06
    POSITIVE LOGITS
    uname
    0.08
    !↵↵
    0.07
    _GREEN
    0.07
    	del
    0.07
     sinon
    0.07
     budeme
    0.07
     respect
    0.07
    τζ
    0.06
     sesame
    0.06
    >'.↵
    0.06
    Act Density 0.084%

    No Known Activations