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

    Neuronpedia

    INDEX
    Explanations

    code/logs/paths

    np_max-act · gemini-2.0-flash

    The neuron flags numeric tokens representing fractional (decimal) values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ngừng
    -0.07
    (CG
    -0.06
    segue
    -0.06
     volum
    -0.06
     Nadu
    -0.06
    укт
    -0.06
     evenly
    -0.06
    Owner
    -0.06
     floating
    -0.06
     코드
    -0.06
    POSITIVE LOGITS
    >@
    0.06
    iscrimination
    0.06
    imps
    0.06
     transporting
    0.06
    ullan
    0.06
    ainers
    0.06
    sig
    0.06
     Tommy
    0.06
    Dick
    0.06
    $template
    0.06
    Act Density 0.000%

    No Known Activations