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

    Neuronpedia

    INDEX
    Explanations

    Code-related punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    reck
    -0.07
     demonstrate
    -0.07
     beet
    -0.06
     đỏ
    -0.06
    ITY
    -0.06
     مکان
    -0.06
     Electronic
    -0.06
    ées
    -0.06
     dveře
    -0.06
     illustration
    -0.06
    POSITIVE LOGITS
     keer
    0.07
    !,
    0.07
     něj
    0.06
    _registers
    0.06
    ,status
    0.06
     Sith
    0.06
     Foo
    0.06
    					↵
    0.06
     Pedido
    0.06
     TFT
    0.06
    Act Density 0.027%

    No Known Activations