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

    Neuronpedia

    INDEX
    Explanations

    assigning

    np_max-act · gemini-2.0-flash

    This neuron primarily detects numeric values—especially decimal numbers or scores—embedded in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    parer
    -0.07
     straně
    -0.06
    _endian
    -0.06
     transporter
    -0.06
    FN
    -0.06
     있습니다
    -0.06
    abad
    -0.06
     parfait
    -0.06
    Denver
    -0.06
     golden
    -0.06
    POSITIVE LOGITS
    ога
    0.07
    
    0.06
    δε
    0.06
     assigning
    0.06
     assigned
    0.06
     freq
    0.06
    ....↵↵
    0.06
     forums
    0.06
    тим
    0.06
     skutečně
    0.06
    Act Density 0.023%

    No Known Activations