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

    Neuronpedia

    INDEX
    Explanations

    Categories

    np_max-act · gemini-2.0-flash

    The neuron activates on standalone decimal‐formatted numbers (floating‐point values) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (fs
    -0.07
    F
    -0.06
     восстанов
    -0.06
     Cluster
    -0.06
    _TRANSFORM
    -0.06
    ових
    -0.06
     Sniper
    -0.06
     '*'
    -0.06
    ीय
    -0.06
     travail
    -0.06
    POSITIVE LOGITS
    -guard
    0.07
    иб
    0.06
     dolor
    0.06
     зак
    0.06
    opard
    0.06
    .ClientSize
    0.06
    uard
    0.06
    بعد
    0.06
     ultimately
    0.06
    _Comm
    0.06
    Act Density 0.009%

    No Known Activations