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

    Neuronpedia

    INDEX
    Explanations

    famous last words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    집합
    0.38
    ્યાં
    0.37
    開放
    0.37
     مطلوب
    0.37
    ビ
    0.36
     অনুসন্ধান
    0.36
    ภาพ
    0.36
     پردا
    0.36
    ニン
    0.36
    襞
    0.35
    POSITIVE LOGITS
     superstitious
    1.31
     j
    1.21
     superstition
    1.21
     superstit
    1.11
     superst
    1.03
     cursed
    1.01
     curse
    0.97
     unlucky
    0.91
     curses
    0.83
    詛
    0.79
    Act Density 0.020%

    No Known Activations