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

    Neuronpedia

    INDEX
    Explanations

    action or resolution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    മില്ല
    0.43
     quotients
    0.43
     convexes
    0.40
    stantially
    0.39
     mixtures
    0.38
     ponctuées
    0.38
     приве
    0.37
     perde
    0.37
     polos
    0.37
     alloys
    0.37
    POSITIVE LOGITS
    尽快
    0.61
     최대한
    0.49
    ANAL
    0.47
    尽可能
    0.46
     segera
    0.45
     ASAP
    0.45
     새로운
    0.44
     critique
    0.43
    刀
    0.42
    Schedule
    0.42
    Act Density 0.002%

    No Known Activations