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

    Neuronpedia

    INDEX
    Explanations

    langle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Daw
    -0.07
    59
    -0.07
    frica
    -0.07
    359
    -0.06
    uchs
    -0.06
    Propagation
    -0.06
    63
    -0.06
    softmax
    -0.06
     sitcom
    -0.06
    share
    -0.06
    POSITIVE LOGITS
     <
    0.07
     대전
    0.07
     sl
    0.07
     admirable
    0.07
     fel
    0.06
    .medium
    0.06
    بط
    0.06
     पत
    0.06
     نج
    0.06
    ,color
    0.06
    Act Density 0.005%

    No Known Activations