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

    Neuronpedia

    INDEX
    Explanations

    include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    appendTo
    -0.07
    DIFF
    -0.07
    .Utilities
    -0.07
    Funny
    -0.07
     модели
    -0.06
    erg
    -0.06
     broth
    -0.06
    azer
    -0.06
    -awaited
    -0.06
     Deng
    -0.06
    POSITIVE LOGITS
    184
    0.06
     الطبي
    0.06
     hydraulic
    0.06
    _SS
    0.06
    藏
    0.06
    AsStream
    0.06
     Veg
    0.05
    看到
    0.05
    ordinate
    0.05
     lik
    0.05
    Act Density 0.011%

    No Known Activations