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

    Neuronpedia

    INDEX
    Explanations

    approximate sizes and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    requently
    0.76
    某
    0.73
    ousands
    0.72
    函
    0.71
     тысячи
    0.68
    某些
    0.66
     нередко
    0.66
    绎
    0.65
    するなど
    0.65
     Said
    0.64
    POSITIVE LOGITS
    Level
    0.65
    uding
    0.62
    치
    0.61
     drept
    0.60
     culminated
    0.60
    tone
    0.60
     igual
    0.60
    like
    0.59
    uar
    0.59
     appropriated
    0.58
    Act Density 0.004%

    No Known Activations