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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash

    The neuron detects subordinating conjunctions and clause-marking discourse words (e.g. if, because, although, since, when, considering).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ে
    -0.07
    jí
    -0.06
    Lines
    -0.06
    usunda
    -0.06
     reluct
    -0.06
     televizyon
    -0.06
    コメント
    -0.06
    кової
    -0.06
    ением
    -0.06
     poem
    -0.06
    POSITIVE LOGITS
     muchos
    0.06
     vowed
    0.06
     scalp
    0.06
     };
    0.06
     yii
    0.06
     Yii
    0.06
     CHtml
    0.06
     gcc
    0.06
    SpecWarn
    0.06
    вит
    0.05
    Act Density 0.094%

    No Known Activations