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

    Neuronpedia

    INDEX
    Explanations

    lists of 0s and 1s

    np_max-act · gemini-2.0-flash

    This neuron detects standalone numeric tokens (number literals) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    raits
    -0.07
    Fi
    -0.07
     �
    -0.06
    澤
    -0.06
    Statements
    -0.06
    Ç
    -0.06
     �
    -0.06
     Coverage
    -0.06
     Forge
    -0.06
     Fighters
    -0.06
    POSITIVE LOGITS
    (inplace
    0.08
     행동
    0.07
     불
    0.07
     tồn
    0.06
    selectedIndex
    0.06
    smtp
    0.06
    -lg
    0.06
    .super
    0.06
    .destination
    0.06
     awful
    0.06
    Act Density 0.014%

    No Known Activations