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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    规模
    -0.08
    ([{
    -0.06
     semble
    -0.06
    fil
    -0.06
    NFL
    -0.06
    нка
    -0.06
    Selector
    -0.06
    Attr
    -0.06
     ocas
    -0.06
    滑
    -0.05
    POSITIVE LOGITS
    ‏
    0.07
     صاح
    0.07
     pra
    0.07
     intermittent
    0.07
    _INSTALL
    0.06
     residential
    0.06
     información
    0.06
     bingo
    0.06
     poner
    0.06
    λω
    0.06
    Act Density 0.046%

    No Known Activations