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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron detects Rust’s `derive(...)` attribute lines, i.e. the trait names listed inside `#[derive(...)]`.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ram
    -0.07
    MR
    -0.06
    руч
    -0.06
    anol
    -0.06
     HM
    -0.06
    ."),
    -0.06
    لمه
    -0.06
    fdb
    -0.06
    .clip
    -0.06
    214
    -0.06
    POSITIVE LOGITS
    //---------------------------------------------------------------------------↵↵
    0.07
     uninitialized
    0.07
     annotations
    0.07
     السكان
    0.07
    [^
    0.07
     indiv
    0.06
    .isSuccessful
    0.06
    oom
    0.06
    ๊
    0.06
     tearDown
    0.06
    Act Density 0.001%

    No Known Activations