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

    Neuronpedia

    INDEX
    Explanations

    may

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric tokens (digits, numbers with decimals, and similar numerical expressions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _BRANCH
    -0.07
    Observer
    -0.07
     Turks
    -0.06
    --------
    -0.06
     EACH
    -0.06
    InChildren
    -0.06
     ↘
    -0.06
    BILE
    -0.06
    AME
    -0.06
    rak
    -0.06
    POSITIVE LOGITS
     conditioner
    0.07
    sing
    0.07
     운동
    0.07
    _fail
    0.07
    ucht
    0.07
    cem
    0.07
     место
    0.07
    vyk
    0.06
     구
    0.06
     lu
    0.06
    Act Density 0.027%

    No Known Activations