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

    Neuronpedia

    INDEX
    Explanations

    alpha

    np_max-act · gemini-2.0-flash

    This neuron activates on “alpha” (especially in “alpha-<term>”) prefixes in biochemical or pharmacological names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     cul
    -0.07
    _sent
    -0.07
     Duis
    -0.07
     negotiation
    -0.07
    گیرد
    -0.07
    Tre
    -0.07
     UIStoryboardSegue
    -0.07
    ,end
    -0.06
    二十
    -0.06
    _List
    -0.06
    POSITIVE LOGITS
     Alpha
    0.14
     alpha
    0.12
    alpha
    0.12
    .Alpha
    0.11
     α
    0.11
     ALPHA
    0.10
    Alpha
    0.10
    -alpha
    0.09
     alph
    0.09
    .alpha
    0.08
    Act Density 0.014%

    No Known Activations