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

    Neuronpedia

    INDEX
    Explanations

    probability of letter sequences

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens representing computed probability values (i.e. floating-point numbers with decimals).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     stru
    -0.07
     unab
    -0.07
    .rest
    -0.07
    _gem
    -0.06
     nett
    -0.06
    .rec
    -0.06
     zi
    -0.06
    vant
    -0.06
     egret
    -0.06
    .Design
    -0.06
    POSITIVE LOGITS
    대한
    0.06
    ßer
    0.06
     pushing
    0.06
    ollapsed
    0.06
    нося
    0.06
    \"";↵
    0.06
     devastation
    0.06
     achieved
    0.06
     Update
    0.06
     $_[
    0.06
    Act Density 0.002%

    No Known Activations