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

    Neuronpedia

    INDEX
    Explanations

    verify information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ڡ
    0.42
     archae
    0.42
    Sheep
    0.39
    sheep
    0.38
    野菜
    0.38
     alber
    0.38
     статью
    0.37
    )');
    0.37
    )-,
    0.37
     apapun
    0.36
    POSITIVE LOGITS
    一般来说
    0.43
     khả
    0.40
     Expansion
    0.38
     crushes
    0.38
    entraînement
    0.37
     core
    0.37
    hart
    0.37
     Fier
    0.37
     Liga
    0.36
     fierce
    0.36
    Act Density 0.000%

    No Known Activations