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

    Neuronpedia

    INDEX
    Explanations

    Question and answer snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    รค
    -0.07
    اور
    -0.07
    _vec
    -0.07
     fatalities
    -0.07
    Decorator
    -0.07
     debating
    -0.07
    _recovery
    -0.07
    ัญญ
    -0.07
    不知道
    -0.07
    苦
    -0.07
    POSITIVE LOGITS
    eature
    0.06
     mít
    0.05
    _refer
    0.05
    ::::::::::::::::::::::::::::::::
    0.05
     แพ
    0.05
     лим
    0.05
     ở
    0.05
     pellets
    0.05
    νια
    0.05
     hrá
    0.05
    Act Density 0.165%

    No Known Activations