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

    Neuronpedia

    INDEX
    Explanations

    numbers and @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sequences
    -0.09
    .commands
    -0.07
     simples
    -0.07
    きれい
    -0.07
     fins
    -0.07
     너무
    -0.07
    통
    -0.07
     createSelector
    -0.07
    dsl
    -0.07
    边上
    -0.07
    POSITIVE LOGITS
    raphics
    0.07
    ؊
    0.07
    �
    0.07
    %
    0.07
    -ph
    0.06
    뒨
    0.06
    🦇
    0.06
     Prior
    0.06
    占据
    0.06
     répond
    0.06
    Act Density 0.016%

    No Known Activations