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

    Neuronpedia

    INDEX
    Explanations

    activities and systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    垛
    0.49
     Morbi
    0.43
    筥
    0.42
    фесси
    0.40
     Format
    0.40
     Parmi
    0.40
     Lyrics
    0.39
    lane
    0.39
     بلی
    0.39
     Beside
    0.38
    POSITIVE LOGITS
    activity
    0.38
    活动
    0.37
    становление
    0.37
    ictive
    0.36
     actions
    0.36
    actions
    0.36
     действия
    0.35
    ium
    0.35
    Maximum
    0.35
    mathspace
    0.35
    Act Density 0.000%

    No Known Activations