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

    Neuronpedia

    INDEX
    Explanations

    on or upon followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    锈钢
    0.42
    inhas
    0.40
     кое
    0.39
     fonbet
    0.38
     भागीदारी
    0.37
     ढाई
    0.36
    稍
    0.36
     choć
    0.36
    ミス
    0.35
    वेयर
    0.35
    POSITIVE LOGITS
    Unnamed
    0.42
    solved
    0.39
     Ara
    0.39
    Tar
    0.37
    āta
    0.37
     jon
    0.36
     aa
    0.35
     ceremony
    0.35
    archa
    0.35
    ᴛ
    0.35
    Act Density 0.000%

    No Known Activations