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

    Neuronpedia

    INDEX
    Explanations

    clear

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of “clear” (especially in the context of clearing history) in UI-related code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -width
    -0.06
     proofs
    -0.06
     कल
    -0.06
     методи
    -0.06
     даже
    -0.06
     depth
    -0.06
    曾
    -0.06
    iddles
    -0.06
    reated
    -0.06
     getUserId
    -0.06
    POSITIVE LOGITS
     PŘ
    0.07
    /source
    0.07
    >(_
    0.06
     уча
    0.06
     zero
    0.06
    GOOD
    0.06
    >)
    0.06
    _srv
    0.06
     bourgeois
    0.06
    İS
    0.06
    Act Density 0.220%

    No Known Activations