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

    Neuronpedia

    INDEX
    Explanations

    signal processing

    np_max-act · gemini-2.0-flash

    The neuron fires on present‐tense engineering action words (especially gerunds ending in “-ing”) that describe signal‐processing steps.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ök
    -0.08
    .RightToLeft
    -0.07
    _tree
    -0.07
     objeto
    -0.07
    _solve
    -0.07
     Pedido
    -0.06
     reputable
    -0.06
    _likes
    -0.06
    iali
    -0.06
     inclu
    -0.06
    POSITIVE LOGITS
    ίναι
    0.06
     کنم
    0.06
    proj
    0.06
    reference
    0.06
     var
    0.06
    nutím
    0.06
     sped
    0.06
    ramids
    0.06
    frica
    0.06
     действ
    0.06
    Act Density 0.018%

    No Known Activations