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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Plymouth
    -0.06
     Ferdinand
    -0.06
     danh
    -0.06
     todd
    -0.06
    umbai
    -0.06
     bland
    -0.06
    /T
    -0.06
    $rs
    -0.06
    thumb
    -0.06
     Alexander
    -0.06
    POSITIVE LOGITS
    (vis
    0.07
    ):
↵
↵
    0.07
    	clock
    0.07
    .Mult
    0.07
     ::=
    0.06
     __________________↵↵
    0.06
    _BIN
    0.06
    fü
    0.06
     safeg
    0.06
     ioctl
    0.06
    Act Density 0.026%

    No Known Activations