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

    Neuronpedia

    INDEX
    Explanations

    creative text formats and sorted lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    0.57
    the
    0.54
    to
    0.53
    lists
    0.52
    CATS
    0.52
    i
    0.52
    EDY
    0.51
    it
    0.49
    labor
    0.49
    cats
    0.49
    POSITIVE LOGITS
    ă
    0.55
     víctima
    0.50
     earliest
    0.48
    观念
    0.48
     사람이
    0.44
    avi
    0.44
     puppy
    0.43
     improvis
    0.43
    づくり
    0.42
    aniya
    0.42
    Act Density 0.000%

    No Known Activations