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

    Neuronpedia

    INDEX
    Explanations

    program files or code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.75
     имеет
    0.73
     పి
    0.72
    дца
    0.72
     начинает
    0.71
     Поскольку
    0.70
    estimates
    0.70
    అ
    0.70
    ÕES
    0.69
     вопло
    0.69
    POSITIVE LOGITS
    تی
    0.71
    整体
    0.70
     manier
    0.70
     Interact
    0.70
     outlook
    0.68
     Cont
    0.68
    श्विक
    0.67
     unis
    0.67
     êtres
    0.67
    Matic
    0.67
    Act Density 0.000%

    No Known Activations