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

    Neuronpedia

    INDEX
    Explanations

    Pig Latin suffix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     shown
    0.34
    '])){
    0.32
     до
    0.29
     شهرستان
    0.29
     लगाकर
    0.29
    lashes
    0.29
     वो
    0.29
    ");*/
    0.29
     شده
    0.28
    くん
    0.28
    POSITIVE LOGITS
    ┑
    0.34
     -.
    0.31
     Immun
    0.30
     TInner
    0.30
     Whilst
    0.29
     ולא
    0.29
     │
    0.29
     καὶ
    0.29
     。
    0.28
    ܀
    0.28
    Act Density 0.000%

    No Known Activations