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

    Neuronpedia

    INDEX
    Explanations

    _offset

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     perplex
    -0.07
    DVD
    -0.07
     Cooperative
    -0.06
    Areas
    -0.06
    atik
    -0.06
    Ret
    -0.06
     Unidos
    -0.06
    =tmp
    -0.06
    	verify
    -0.06
     Katz
    -0.06
    POSITIVE LOGITS
    legg
    0.07
     thịt
    0.07
     갤
    0.06
    .General
    0.06
    .vendor
    0.06
    emailer
    0.06
    hetics
    0.06
    %!
    0.06
     AppBar
    0.06
    ẩy
    0.06
    Act Density 0.003%

    No Known Activations