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

    Neuronpedia

    INDEX
    Explanations

    target

    np_max-act · gemini-2.0-flash

    The neuron activates on references to software or platform version numbers (e.g., Xcode, iOS, SDK, deployment targets).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     आध
    -0.07
     Його
    -0.06
     ONE
    -0.06
    いる
    -0.06
     httpClient
    -0.06
     SUM
    -0.06
    .Enc
    -0.06
    еред
    -0.06
    ortho
    -0.06
    _MEMBERS
    -0.06
    POSITIVE LOGITS
    /options
    0.07
    “For
    0.07
    .ts
    0.07
     NRL
    0.07
     кас
    0.06
    zept
    0.06
    .SelectedIndexChanged
    0.06
     Integrated
    0.06
     historical
    0.06
     Daughter
    0.06
    Act Density 0.016%

    No Known Activations