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

    Neuronpedia

    INDEX
    Explanations

    high-pass filter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     botão
    0.38
    ボタン
    0.37
    驛
    0.37
     الرسمي
    0.37
    បញ្ចូល
    0.36
     menú
    0.36
    𝖚
    0.35
    क्वल
    0.35
    োর্স
    0.35
     MARC
    0.35
    POSITIVE LOGITS
    oure
    0.38
    rola
    0.38
    shorts
    0.37
     Colle
    0.37
    urut
    0.37
    shy
    0.37
    sh
    0.36
    rah
    0.36
    ukuran
    0.35
     ख़
    0.35
    Act Density 0.001%

    No Known Activations