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

    Neuronpedia

    INDEX
    Explanations

    babel

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literals with decimal points (floating‐point numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    кової
    -0.07
     voz
    -0.07
    LAT
    -0.06
    чист
    -0.06
     trữ
    -0.06
     NSLayoutConstraint
    -0.06
    цями
    -0.06
    ニﾆ
    -0.06
    니아
    -0.06
    лиж
    -0.06
    POSITIVE LOGITS
    -blind
    0.07
     correspondence
    0.07
     adec
    0.07
    aturity
    0.07
     "__
    0.07
    κει
    0.06
     borrowed
    0.06
    被
    0.06
    rong
    0.06
     presidents
    0.06
    Act Density 0.004%

    No Known Activations