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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash

    The neuron fires on verbs that describe device‐repair actions (especially gerunds or imperatives like restoring, downgrading, updating, moving, turning, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Suddenly
    -0.07
    Nil
    -0.06
    ignty
    -0.06
    मह
    -0.06
    ान
    -0.06
    enment
    -0.06
    Users
    -0.06
    Suddenly
    -0.06
    اهر
    -0.06
    生
    -0.06
    POSITIVE LOGITS
     galer
    0.07
     δη
    0.06
     vale
    0.06
     Basketball
    0.06
    Wie
    0.06
    <Base
    0.06
    (chart
    0.05
    ntp
    0.05
    ")]↵↵
    0.05
    \">↵
    0.05
    Act Density 0.362%

    No Known Activations