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

    Neuronpedia

    INDEX
    Explanations

    significant differences by margin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     durumu
    0.52
     rosto
    0.45
     territory
    0.44
     형태
    0.41
     situation
    0.40
     ситуации
    0.40
     ámbito
    0.39
     অবস্থায়
    0.39
     território
    0.38
    რულ
    0.38
    POSITIVE LOGITS
     dint
    0.76
     virtue
    0.71
     means
    0.68
    means
    0.60
    手段
    0.54
     wayside
    0.53
     biais
    0.52
     standards
    0.49
     moyens
    0.48
    margin
    0.47
    Act Density 0.013%

    No Known Activations