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

    Neuronpedia

    INDEX
    Explanations

    time and opportunity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Times
    0.38
     Exped
    0.38
     Times
    0.37
     irregularly
    0.37
    铱
    0.37
     Slab
    0.36
     προς
    0.36
    %、
    0.36
    Define
    0.36
    లి
    0.35
    POSITIVE LOGITS
     ample
    1.26
    ample
    0.96
     فرص
    0.91
     plenty
    0.89
    時間が
    0.86
    時間を
    0.86
     الوقت
    0.86
     സമയം
    0.84
     tijd
    0.84
     시간을
    0.84
    Act Density 0.032%

    No Known Activations