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
    كم
    -0.07
    벤
    -0.07
     wir
    -0.07
    ů
    -0.07
     khi
    -0.06
    恿
    -0.06
    jść
    -0.06
    ij
    -0.06
    Correo
    -0.06
     "{{
    -0.06
    POSITIVE LOGITS
    _trans
    0.08
    (where
    0.07
    -ap
    0.07
    TableRow
    0.07
    =A
    0.07
    heap
    0.07
    -done
    0.07
    のように
    0.07
     ולאחר
    0.07
    墣
    0.07
    Act Density 0.042%

    No Known Activations