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

    Neuronpedia

    INDEX
    Explanations

    Code examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     McDonald
    -0.07
     SL
    -0.07
    atrigesimal
    -0.06
    сл
    -0.06
     duration
    -0.06
    _Type
    -0.06
     Stream
    -0.06
     günü
    -0.06
     Server
    -0.06
     producers
    -0.06
    POSITIVE LOGITS
    �
    0.07
    .","
    0.06
     превыш
    0.06
    .stopPropagation
    0.06
    lixir
    0.06
    岁
    0.06
     国产
    0.06
    _TAGS
    0.06
     voks
    0.06
     чист
    0.06
    Act Density 0.042%

    No Known Activations