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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reserves
    -0.07
    tk
    -0.07
     tubes
    -0.07
     solitude
    -0.07
     fueron
    -0.07
     música
    -0.07
     peri
    -0.07
    SAVE
    -0.06
    ()-
    -0.06
     patch
    -0.06
    POSITIVE LOGITS
    锦
    0.07
    xlim
    0.06
    衣
    0.06
    yped
    0.06
    'utilisation
    0.06
    ="{!!
    0.06
    едаг
    0.06
    漏
    0.06
    Він
    0.06
    (mysqli
    0.06
    Act Density 0.035%

    No Known Activations