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

    Neuronpedia

    INDEX
    Explanations

    Code/Programming

    np_max-act · gemini-2.0-flash

    The neuron detects numeric literals (especially floating‐point numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    kah
    -0.07
    \Routing
    -0.07
     headaches
    -0.07
    Recognizer
    -0.07
    Levels
    -0.07
     imageView
    -0.06
     ArrayBuffer
    -0.06
    .Dial
    -0.06
     REFERENCES
    -0.06
    root
    -0.06
    POSITIVE LOGITS
     weiß
    0.08
     právě
    0.07
     FontAwesome
    0.07
    ması
    0.07
     confidently
    0.07
     ASE
    0.06
     Hayes
    0.06
     електрон
    0.06
    453
    0.06
     seçim
    0.06
    Act Density 0.045%

    No Known Activations