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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    commands and operations related to system processes in code.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron flags code‐style function or command names (e.g. identifiers with trailing “()” or common CLI tool names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     elde
    -0.07
    apel
    -0.07
    幹
    -0.07
     forestry
    -0.06
    Boundary
    -0.06
     cake
    -0.06
     elites
    -0.06
     wiping
    -0.06
     Millet
    -0.06
     Cake
    -0.06
    POSITIVE LOGITS
     )
↵
    0.07
    ;i
    0.06
    ((((
    0.06
    -producing
    0.06
     máte
    0.06
     flashlight
    0.06
    .mj
    0.06
    _INF
    0.06
    :!
    0.06
     tienen
    0.06
    Act Density 0.123%

    No Known Activations