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

    Neuronpedia

    INDEX
    Explanations

    pig latin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    prits
    0.39
     similares
    0.34
     akin
    0.34
    suk
    0.33
    sync
    0.33
    imension
    0.32
     sinn
    0.32
     defensively
    0.32
    焦点
    0.31
    ට්
    0.31
    POSITIVE LOGITS
     charts
    0.69
     chart
    0.64
     formulas
    0.57
     Charts
    0.57
     easiest
    0.55
     quickest
    0.53
     formula
    0.52
     simplest
    0.51
     tables
    0.51
     tricky
    0.51
    Act Density 0.000%

    No Known Activations