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

    Neuronpedia

    INDEX
    Explanations

    expression of relief or gratitude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    could
    0.51
    v
    0.50
     lucky
    0.49
    lucky
    0.48
     luck
    0.46
     unlucky
    0.45
    を楽しむ
    0.45
    t
    0.45
    might
    0.45
     could
    0.44
    POSITIVE LOGITS
     제한
    0.51
     refrained
    0.49
     Limitations
    0.48
     Kein
    0.44
    Limitations
    0.43
     소프트
    0.43
     немає
    0.42
     kein
    0.42
     contamos
    0.42
     সফ
    0.42
    Act Density 0.005%

    No Known Activations