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

    Neuronpedia

    INDEX
    Explanations

    line

    np_max-act · gemini-2.0-flash

    This neuron detects decimal numeric literals (floating‐point numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    gorithms
    -0.08
    okus
    -0.07
    cház
    -0.07
     deselect
    -0.07
     jogging
    -0.07
    gap
    -0.07
    abyrin
    -0.07
    NavLink
    -0.07
    us
    -0.06
     baseUrl
    -0.06
    POSITIVE LOGITS
    ",'
    0.06
     शर
    0.06
    Small
    0.06
    une
    0.06
     eas
    0.06
     【
    0.06
     vowed
    0.06
     thác
    0.06
     indefinite
    0.06
     акти
    0.06
    Act Density 0.014%

    No Known Activations