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

    Neuronpedia

    INDEX
    Explanations

    designed to displace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     செயல்பா
    0.43
     watchful
    0.41
     całkow
    0.40
    Guided
    0.40
    imha
    0.39
     Haver
    0.39
    合計
    0.39
    靕
    0.38
     sombre
    0.38
     право
    0.38
    POSITIVE LOGITS
    temperatur
    0.39
     拉
    0.39
    lug
    0.38
    nica
    0.38
    ɲ
    0.38
    bash
    0.37
    itesse
    0.37
    column
    0.36
    ὖ
    0.36
     ня
    0.36
    Act Density 0.000%

    No Known Activations