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

    Neuronpedia

    INDEX
    Explanations

    code and urls

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     explicitly
    0.44
     omitting
    0.39
     ignored
    0.37
    0.37
     TextBox
    0.37
    <unused2164>
    0.36
     Horror
    0.36
    "]},
    0.36
     List
    0.35
     ←
    0.35
    POSITIVE LOGITS
    运用
    0.36
     operandSize
    0.36
    珬
    0.36
     баскетбол
    0.34
     फरार
    0.33
     únic
    0.33
     slowmotion
    0.33
     moyenne
    0.33
     जगदीश
    0.33
     anciennes
    0.33
    Act Density 0.133%

    No Known Activations