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

    Neuronpedia

    INDEX
    Explanations

    Code and configurations

    np_max-act · gemini-2.0-flash

    This neuron primarily activates on numeric tokens (digits or numbers) within the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _Message
    -0.07
    길
    -0.07
    .interpolate
    -0.07
    片
    -0.07
     almış
    -0.07
    HashSet
    -0.07
     آزم
    -0.07
    .look
    -0.07
    remote
    -0.07
    anela
    -0.07
    POSITIVE LOGITS
    _MAIN
    0.06
     feud
    0.06
     вий
    0.06
    [dim
    0.06
    ried
    0.06
    atoria
    0.06
     спе
    0.05
    „N
    0.05
     типу
    0.05
    marker
    0.05
    Act Density 0.047%

    No Known Activations