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

    Neuronpedia

    INDEX
    Explanations

    finding matches or similarities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    heh
    0.42
    꼐
    0.41
     связаны
    0.39
     khổ
    0.39
    REL
    0.39
    ಹಾರ
    0.39
     relaciones
    0.38
    Yam
    0.38
    镓
    0.38
    plication
    0.38
    POSITIVE LOGITS
     match
    0.93
     Match
    0.87
    match
    0.84
    匹配
    0.79
     wits
    0.79
     MATCH
    0.77
     matcher
    0.77
     matching
    0.76
    マッチ
    0.75
     matches
    0.74
    Act Density 0.011%

    No Known Activations