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

    Neuronpedia

    INDEX
    Explanations

    audio engineering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     중요
    0.49
    ியா
    0.47
     sagittis
    0.47
    ẓ
    0.46
     божомолдору
    0.45
     monstros
    0.45
    𝙠
    0.45
     тощо
    0.45
    銜
    0.45
     ска
    0.44
    POSITIVE LOGITS
    ,
    0.42
     Schur
    0.40
     piek
    0.40
    5
    0.39
    9
    0.39
     Klein
    0.38
    CID
    0.38
    8
    0.37
     Rico
    0.37
     recursive
    0.37
    Act Density 0.004%

    No Known Activations