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

    Neuronpedia

    INDEX
    Explanations

    Research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .numpy
    -0.07
    有些人
    -0.07
    オ
    -0.06
    -check
    -0.06
    遍
    -0.06
     experimented
    -0.06
    فيدي
    -0.06
     sweating
    -0.06
     Saudis
    -0.06
     ليست
    -0.06
    POSITIVE LOGITS
     rivals
    0.07
    ‵
    0.07
    )]
↵
    0.07
     EFFECT
    0.07
     בהתאם
    0.07
    ”.
    0.06
    灵敏
    0.06
                                  ↵
    0.06
    ką
    0.06
     kaldır
    0.06
    Act Density 0.381%

    No Known Activations