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

    Neuronpedia

    INDEX
    Explanations

    /*

    np_max-act · gemini-2.0-flash

    The neuron activates on block‐comment delimiters and lines within block comments (e.g. “/*” and leading “*”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     opposed
    -0.06
     communicated
    -0.06
     sociales
    -0.06
     Hyde
    -0.06
    ;(
    -0.06
    issing
    -0.06
    .Material
    -0.06
     advise
    -0.06
     stitches
    -0.06
     Tir
    -0.06
    POSITIVE LOGITS
    allows
    0.07
    ket
    0.07
     dağı
    0.07
     Sprint
    0.06
    важа
    0.06
    _OBJ
    0.06
    sitemap
    0.06
    .querySelector
    0.06
     nackte
    0.06
    (bytes
    0.06
    Act Density 0.005%

    No Known Activations