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

    Neuronpedia

    INDEX
    Explanations

    common, popular, specific states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     saat
    0.54
     as
    0.50
     and
    0.50
     organisasi
    0.48
     animal
    0.47
     panel
    0.47
     sebagai
    0.47
     bukan
    0.47
     pasien
    0.47
     textile
    0.47
    POSITIVE LOGITS
    市区
    0.49
    敌
    0.48
    ೂರ್ವ
    0.46
    ートル
    0.46
    ᶰ
    0.46
    రా
    0.45
    Bour
    0.44
    ัน
    0.44
    हू
    0.43
    菈
    0.43
    Act Density 0.006%

    No Known Activations