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

    Neuronpedia

    INDEX
    Explanations

    running hello world program

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trivially
    0.41
     файл
    0.39
    Abs
    0.37
     ABS
    0.37
    ница
    0.37
    Tar
    0.37
    遒
    0.37
    afe
    0.36
    dzić
    0.36
    Lie
    0.36
    POSITIVE LOGITS
    ইউনি
    0.41
     erratic
    0.40
     compartments
    0.37
     возгла
    0.36
     tjän
    0.36
     turban
    0.36
    人間の
    0.36
     chasse
    0.35
     tainted
    0.35
     zase
    0.35
    Act Density 0.000%

    No Known Activations