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

    Neuronpedia

    INDEX
    Explanations

    math and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bringing
    -0.07
     Marcos
    -0.06
     Checker
    -0.06
     pros
    -0.06
     ฟร
    -0.06
     proposing
    -0.06
    _arrays
    -0.06
    ANGUAGE
    -0.06
    acellular
    -0.06
    (success
    -0.06
    POSITIVE LOGITS
    ανδ
    0.07
    __)↵↵↵
    0.07
    -coordinate
    0.06
    instrument
    0.06
    енд
    0.06
    -graph
    0.06
    @return
    0.06
     LIC
    0.06
     appendString
    0.06
    iêng
    0.06
    Act Density 0.002%

    No Known Activations