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

    Neuronpedia

    INDEX
    Explanations

    AI alignment and STEM education

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    1.05
    нар
    0.86
    ている
    0.82
     চাঁদপুর
    0.81
    ⚭
    0.80
    ले
    0.80
    인트
    0.77
    ö
    0.75
    Leffler
    0.73
    댁
    0.73
    POSITIVE LOGITS
    meng
    0.93
    лт
    0.92
     remem
    0.91
    MENTS
    0.91
    :
    0.90
    rences
    0.88
     elas
    0.87
     .
    0.86
    𝐂
    0.86
     morto
    0.83
    Act Density 0.064%

    No Known Activations