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

    Neuronpedia

    INDEX
    Explanations

    minimizing restraints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     különböző
    0.82
     تیم
    0.79
    ל
    0.76
     těž
    0.75
    ƅ
    0.74
     طراحی
    0.74
     डिप्टी
    0.74
     producción
    0.73
    틸
    0.73
     های
    0.73
    POSITIVE LOGITS
    nél
    0.79
    nets
    0.78
    nent
    0.76
    nT
    0.73
    cation
    0.72
    nThe
    0.72
    iate
    0.71
    ⊰
    0.71
    ,...,
    0.71
    n
    0.71
    Act Density 0.000%

    No Known Activations