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

    Neuronpedia

    INDEX
    Explanations

    may

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Official
    -0.08
    녤
    -0.08
    ذهب
    -0.08
     Санкт
    -0.08
    nee
    -0.07
    쫓
    -0.07
    school
    -0.07
    쨍
    -0.07
    Js
    -0.07
    سود
    -0.06
    POSITIVE LOGITS
    (',')↵
    0.07
     craw
    0.07
    xb
    0.06
    .Mutex
    0.06
    _collection
    0.06
     ص
    0.06
    	then
    0.06
     בר
    0.06
    ition
    0.06
    aces
    0.06
    Act Density 0.004%

    No Known Activations