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

    Neuronpedia

    INDEX
    Explanations

    importing code libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Snell
    0.36
     Yeah
    0.35
     Suck
    0.35
     Memorial
    0.35
    ่
    0.35
     Zack
    0.35
    0
    0.34
     remem
    0.34
    ဖြ
    0.34
     Lembrando
    0.34
    POSITIVE LOGITS
     함수
    0.34
     robot
    0.33
     فونبټ
    0.32
     دائو
    0.31
     robots
    0.30
     funcao
    0.30
    遊戲
    0.30
     게임
    0.30
    クラス
    0.30
     compliqué
    0.30
    Act Density 0.026%

    No Known Activations