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

    Neuronpedia

    INDEX
    Explanations

    not or unless

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bzw
    0.40
    ຳ
    0.35
     {@
    0.34
    ユーザー
    0.33
     Lubric
    0.33
    氟
    0.33
     Tuberculosis
    0.33
     iç
    0.32
     অয়েল
    0.32
    证
    0.32
    POSITIVE LOGITS
    have
    0.44
    few
    0.35
    Unless
    0.35
     than
    0.35
    been
    0.34
     slightest
    0.34
    Few
    0.32
     been
    0.31
     have
    0.31
    has
    0.31
    Act Density 0.006%

    No Known Activations