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

    Neuronpedia

    INDEX
    Explanations

    'tis contraction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ქმედ
    0.73
    olt
    0.71
    chtig
    0.66
     amplification
    0.65
     amplifying
    0.64
    gement
    0.62
    စီး
    0.61
     брига
    0.61
    gna
    0.61
    有趣
    0.60
    POSITIVE LOGITS
    Join
    0.87
     join
    0.86
     rejoined
    0.86
    join
    0.80
     joining
    0.79
    member
    0.77
    Tween
    0.75
     joins
    0.74
     rejoint
    0.74
     Join
    0.72
    Act Density 0.001%

    No Known Activations