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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash

    This neuron activates on parenthetical or quoted alternate names/translations (e.g. the “or” ‑ style appositions and foreign-language terms in parentheses or quotes).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _triangle
    -0.07
     crater
    -0.06
     repairing
    -0.06
    _ptr
    -0.06
     infuri
    -0.06
    ikler
    -0.06
     ItemType
    -0.06
     ارزیابی
    -0.06
     Witch
    -0.06
     UIP
    -0.06
    POSITIVE LOGITS
    -prepend
    0.06
    Yu
    0.06
     लगत
    0.06
    _embed
    0.06
    opc
    0.06
     wallet
    0.06
    须
    0.06
    hawks
    0.06
     serpent
    0.06
    '|
    0.05
    Act Density 0.056%

    No Known Activations