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

    Neuronpedia

    INDEX
    Explanations

    duration or time limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ଠ
    0.65
     Einst
    0.62
    くに
    0.61
    iam
    0.61
    早就
    0.60
     Organiz
    0.60
    ectic
    0.59
    निष्कर्ष
    0.58
     अवल
    0.58
    पूर्व
    0.58
    POSITIVE LOGITS
     لمدة
    2.79
     temporarily
    2.31
     briefly
    2.31
     momentarily
    2.11
     until
    2.09
    until
    1.99
     indefinitely
    1.97
    Until
    1.88
     Until
    1.87
    しばらく
    1.86
    Act Density 0.260%

    No Known Activations