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

    Neuronpedia

    INDEX
    Explanations

    however

    np_max-act · gemini-2.0-flash

    The neuron consistently lights up on numeric tokens (especially float‐style numbers with decimal points).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _games
    -0.07
     fav
    -0.06
    	push
    -0.06
    _EDIT
    -0.06
     віз
    -0.06
    Με
    -0.06
    NSDictionary
    -0.06
    scribed
    -0.06
     payment
    -0.06
    	tx
    -0.06
    POSITIVE LOGITS
    itler
    0.08
     \↵
    0.08
     \
↵
    0.06
    ($(".
    0.06
    categorie
    0.06
    ]*
    0.06
     istiyorum
    0.06
     personn
    0.06
     moc
    0.06
    .Commit
    0.06
    Act Density 0.377%

    No Known Activations