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

    Neuronpedia

    INDEX
    Explanations

    commas and x

    np_max-act · gemini-2.0-flash

    The neuron consistently lights up on numeric literals—especially floating-point constants—scattered throughout the source.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -free
    -0.07
    Aud
    -0.07
    _DH
    -0.07
    Assistant
    -0.06
    �
    -0.06
    .axis
    -0.06
    death
    -0.06
    -res
    -0.06
    -feature
    -0.06
    enance
    -0.06
    POSITIVE LOGITS
    useRalative
    0.07
     Grund
    0.06
    mesini
    0.06
     Adobe
    0.06
     basket
    0.06
     rooted
    0.06
    єте
    0.06
    .esp
    0.06
     раск
    0.06
     obsahuje
    0.06
    Act Density 0.193%

    No Known Activations