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

    Neuronpedia

    INDEX
    Explanations

    No distinguishable pattern found

    np_acts-logits-general · gemini-2.5-flash-lite

    AI interaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ı
    0.66
    ку
    0.62
    кия
    0.61
    only
    0.59
    ки
    0.57
     mjes
    0.57
    کم
    0.57
    ều
    0.56
    ле
    0.55
    sofar
    0.55
    POSITIVE LOGITS
     on
    0.60
    (
    0.57
     is
    0.57
     Ejército
    0.54
     Prevalence
    0.52
     at
    0.51
     Playhouse
    0.51
     Treasures
    0.50
    \
    0.50
     灬
    0.49
    Act Density 0.000%

    No Known Activations