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

    Neuronpedia

    INDEX
    Explanations

    auxiliary languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Audiobook
    0.95
    まとめ
    0.74
    ৃঙ্খলা
    0.73
     publique
    0.71
    ຼ
    0.71
    ща
    0.71
    nings
    0.70
    жин
    0.70
    enez
    0.70
    ﺠ
    0.70
    POSITIVE LOGITS
     olnud
    0.77
    ก
    0.76
     quaisquer
    0.75
     silencio
    0.72
    름
    0.70
     qualquer
    0.70
    후
    0.69
    Apellido
    0.68
    跋
    0.68
    ⊠
    0.66
    Act Density 0.001%

    No Known Activations