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

    Neuronpedia

    INDEX
    Explanations

    could/have

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ').'</
    -0.07
     입니다
    -0.07
    ertura
    -0.07
    PageRoute
    -0.06
    %D
    -0.06
    ['<{
    -0.06
    .insert
    -0.06
     füh
    -0.06
    "])
↵
    -0.06
    Você
    -0.06
    POSITIVE LOGITS
    _so
    0.08
    mem
    0.07
     MAN
    0.07
    339
    0.07
     Deal
    0.07
    READ
    0.06
    kom
    0.06
    859
    0.06
    -reader
    0.06
     Null
    0.06
    Act Density 0.034%

    No Known Activations