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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron is triggered by comment‐style license headers (lines beginning with “//” or “/*” and copyright/license wording).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ışık
    -0.07
    學
    -0.06
    евых
    -0.06
    .Tick
    -0.06
     depicting
    -0.06
    Dark
    -0.06
     اختص
    -0.06
     denomination
    -0.06
     Taiwanese
    -0.06
     mev
    -0.06
    POSITIVE LOGITS
    deserialize
    0.08
    reiben
    0.07
    /as
    0.07
    >';↵
    0.06
    ActionCreators
    0.06
    unlock
    0.06
     rust
    0.06
     stability
    0.06
    error
    0.06
    は
    0.06
    Act Density 0.004%

    No Known Activations