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

    Neuronpedia

    INDEX
    Explanations

    HOTAS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hesitate
    1.58
    그러나
    1.52
    арма
    1.46
    या
    1.37
     coaxial
    1.32
    भाविक
    1.30
    oarthritis
    1.29
    இந்திய
    1.28
    いは
    1.27
     weaken
    1.27
    POSITIVE LOGITS
    𝙩
    1.56
    AX
    1.53
    ).'
    1.49
     userID
    1.46
    ೂ
    1.46
    )};
    1.45
    j
    1.45
    FUL
    1.44
    .`
    1.43
    ɖ
    1.42
    Act Density 0.000%

    No Known Activations