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

    Neuronpedia

    INDEX
    Explanations

    ; )

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numeric literals (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    perial
    -0.07
    hosts
    -0.07
     drinkers
    -0.06
    กลาง
    -0.06
     registration
    -0.06
     Licensed
    -0.06
    viders
    -0.06
    cem
    -0.06
    愿
    -0.06
    女性
    -0.06
    POSITIVE LOGITS
     điểm
    0.06
    ΩΝ
    0.06
     kern
    0.06
    getObject
    0.06
    ων
    0.06
    (GL
    0.06
    />
↵
    0.06
     blockers
    0.06
    يانة
    0.06
     grind
    0.06
    Act Density 0.030%

    No Known Activations