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

    Neuronpedia

    INDEX
    Explanations

    American Google Docs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    機能
    0.66
    バンド
    0.63
    मू
    0.62
    klasse
    0.62
    ManyToMany
    0.61
    機能を
    0.61
     eyepiece
    0.61
     functionally
    0.61
     stepper
    0.59
     Verdana
    0.59
    POSITIVE LOGITS
    GU
    0.56
    ө
    0.55
     Tibetan
    0.54
    营
    0.54
    நல்ல
    0.52
    Gu
    0.51
    ｔ
    0.50
     rive
    0.50
     गो
    0.49
     Guides
    0.49
    Act Density 0.213%

    No Known Activations