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

    Neuronpedia

    INDEX
    Explanations

    &

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    щие
    -0.07
    似的
    -0.06
     saved
    -0.06
     Identity
    -0.06
     implicated
    -0.06
    -cycle
    -0.06
     gravel
    -0.06
    -water
    -0.06
    Ids
    -0.06
    *>(
    -0.06
    POSITIVE LOGITS
    )),
↵
    0.07
     )),↵
    0.07
    куль
    0.07
    ){
↵
    0.07
     __________________↵↵
    0.07
     قلب
    0.07
    [now
    0.06
     여기
    0.06
     ""),↵
    0.06
    ').'</
    0.06
    Act Density 0.001%

    No Known Activations