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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     VII
    -0.07
     F
    -0.07
     C
    -0.07
    م
    -0.07
    matcher
    -0.06
    F
    -0.06
     T
    -0.06
     B
    -0.06
     Z
    -0.06
    izr
    -0.06
    POSITIVE LOGITS
    ="\
    0.06
     rebell
    0.06
    .Ag
    0.06
    %"),↵
    0.06
    .GetChild
    0.06
    	TArray
    0.06
    (sock
    0.06
     прип
    0.06
    荒
    0.05
     الجز
    0.05
    Act Density 0.092%

    No Known Activations