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

    Neuronpedia

    INDEX
    Explanations

    referencing text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     retrouve
    1.12
     artistique
    1.07
     VFX
    1.04
     Multiplayer
    0.98
     midi
    0.96
    劇情
    0.96
     retrouver
    0.94
    剧情
    0.94
     espectadores
    0.93
     raconte
    0.91
    POSITIVE LOGITS
    《
    1.00
    ：《
    0.97
    󰡔
    0.96
     육
    0.95
     කළ
    0.94
     『
    0.92
     "./
    0.91
     《
    0.91
     "'
    0.91
     ENABLE
    0.90
    Act Density 0.285%

    No Known Activations