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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literal tokens—especially floating‐point constants—within code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    770
    -0.07
    aman
    -0.06
    В
    -0.06
    orro
    -0.06
    Dismiss
    -0.06
     Ven
    -0.06
    Payments
    -0.06
     السعود
    -0.06
     problémy
    -0.06
    513
    -0.06
    POSITIVE LOGITS
    Wolf
    0.06
    zug
    0.06
    ').'
    0.06
    \Plugin
    0.06
    scriptId
    0.06
     ・
    0.06
     crave
    0.06
    namespace
    0.06
    Facing
    0.05
    .apply
    0.05
    Act Density 0.002%

    No Known Activations