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

    Neuronpedia

    INDEX
    Explanations

    which

    np_max-act · gemini-2.0-flash

    The neuron detects clause‐linking function words—especially relative pronouns and auxiliaries that introduce subordinate or future clauses.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    必要
    -0.07
    SCI
    -0.07
    ад
    -0.06
    адки
    -0.06
    Compiler
    -0.06
     工
    -0.06
    _album
    -0.06
     surpass
    -0.06
    ัม
    -0.06
    工
    -0.06
    POSITIVE LOGITS
     azt
    0.07
     Киє
    0.07
    .kotlin
    0.07
    checker
    0.07
    "
↵
    0.06
    ..↵
    0.06
    ));
↵
    0.06
     {
↵
    0.06
    ([])↵
    0.06
    .pm
    0.06
    Act Density 0.064%

    No Known Activations