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

    Neuronpedia

    INDEX
    Explanations

    roots

    np_max-act · gemini-2.0-flash

    The neuron is detecting decimal‐formatted (floating‐point) numbers in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _PULL
    -0.06
    wdx
    -0.06
     wich
    -0.06
    Metric
    -0.06
     Rahman
    -0.06
    ゲ
    -0.06
    ITU
    -0.06
    Grow
    -0.06
    errer
    -0.06
    Fly
    -0.06
    POSITIVE LOGITS
    ------↵↵
    0.07
     discrim
    0.06
    lopedia
    0.06
     stos
    0.06
     différents
    0.06
     photographic
    0.06
     сни
    0.06
    ole
    0.06
     activist
    0.06
    久
    0.06
    Act Density 0.006%

    No Known Activations