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

    Neuronpedia

    INDEX
    Explanations

    Number sorting

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens—integers, decimals, and fractions—wherever they appear.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    출장샵
    -0.07
    Greg
    -0.07
     들
    -0.07
    �
    -0.06
    蜜
    -0.06
     IOC
    -0.06
    是在
    -0.06
     всю
    -0.06
    .getB
    -0.06
    >Status
    -0.06
    POSITIVE LOGITS
    ista
    0.08
    _STORAGE
    0.07
    ute
    0.07
    _PRINT
    0.07
    ör
    0.06
     Spell
    0.06
    ulos
    0.06
     Cheat
    0.06
     ligne
    0.06
    [first
    0.06
    Act Density 0.008%

    No Known Activations