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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting fragments of pasted‐in URLs (especially the random alphanumeric parts of external pastebin‐style links).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     FAST
    -0.07
     Bruce
    -0.06
    .faces
    -0.06
    麼
    -0.06
     incl
    -0.06
    t
    -0.06
    .neg
    -0.06
    (window
    -0.06
    .comp
    -0.06
     participating
    -0.06
    POSITIVE LOGITS
     Ink
    0.07
    ocuk
    0.06
     akt
    0.06
     veil
    0.06
    .Void
    0.06
     centro
    0.06
    InBackground
    0.06
    ніш
    0.06
     recursively
    0.06
    (!_
    0.06
    Act Density 0.002%

    No Known Activations