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

    Neuronpedia

    INDEX
    Explanations

    AI riders personality tactics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +",
    0.48
    ための
    0.46
     больших
    0.45
    +%
    0.44
    ंजा
    0.43
    +')
    0.42
     Sometimes
    0.42
    िंग
    0.42
    もの
    0.41
    マス
    0.41
    POSITIVE LOGITS
    S
    0.47
     mentored
    0.45
     jacket
    0.44
    Krist
    0.43
     league
    0.43
    marshaller
    0.42
    LIK
    0.42
     coached
    0.41
    league
    0.41
     片
    0.40
    Act Density 0.000%

    No Known Activations