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

    Neuronpedia

    INDEX
    Explanations

    tailor to specific needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     αυτές
    0.41
    陖
    0.38
    +}
    0.36
    ?...
    0.36
    ēja
    0.36
    かもしれませんが
    0.35
    <0xE3>
    0.35
     правило
    0.35
     sugger
    0.35
     subspecies
    0.34
    POSITIVE LOGITS
     .”
    0.45
    .“
    0.44
     Новости
    0.41
    “.
    0.40
     ».
    0.40
    》。
    0.39
    .«
    0.39
    .].
    0.39
    ».
    0.39
    ]].
    0.39
    Act Density 0.003%

    No Known Activations