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

    Neuronpedia

    INDEX
    Explanations

    language and text generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tuesday
    0.50
     you
    0.48
     when
    0.48
     an
    0.47
     rehears
    0.45
     once
    0.45
     they
    0.45
     can
    0.44
     two
    0.44
     video
    0.44
    POSITIVE LOGITS
    ಂತ್ರ
    0.49
    慑
    0.47
    طة
    0.47
    椇
    0.47
    وبات
    0.46
    䞍
    0.46
    蕈
    0.45
    栆
    0.45
    枼
    0.45
    水量
    0.44
    Act Density 0.003%

    No Known Activations