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

    Neuronpedia

    INDEX
    Explanations

    ex

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens, i.e. sequences of digits.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Thomas
    -0.06
     Všech
    -0.06
    	counter
    -0.06
     网
    -0.06
     Anal
    -0.06
     weekend
    -0.06
    	full
    -0.06
    	fields
    -0.06
    сий
    -0.06
    ーの
    -0.06
    POSITIVE LOGITS
    ecute
    0.07
     fearing
    0.06
    -lined
    0.06
    ✔
    0.06
     приход
    0.06
     comet
    0.06
     certified
    0.06
    ???
    0.06
     Trainer
    0.06
     nek
    0.06
    Act Density 0.003%

    No Known Activations