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

    Neuronpedia

    INDEX
    Explanations

    object properties or values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     membuatnya
    0.44
    THANK
    0.41
    SPRAY
    0.41
    褥
    0.39
     тях
    0.39
    课堂
    0.36
    mkdirs
    0.36
    ী
    0.36
     abordar
    0.36
    า
    0.35
    POSITIVE LOGITS
     our
    0.45
    हमारी
    0.45
     meine
    0.44
     எங்கள்
    0.43
     unsere
    0.42
     действу
    0.41
     savent
    0.41
     અમારી
    0.39
     हमरे
    0.39
     моих
    0.39
    Act Density 0.016%

    No Known Activations