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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getChild
    -0.08
    올
    -0.07
     Minister
    -0.07
     doanh
    -0.07
     Lem
    -0.07
     châu
    -0.06
     hoàng
    -0.06
     شمال
    -0.06
    HAVE
    -0.06
    have
    -0.06
    POSITIVE LOGITS
     printf
    0.07
     setName
    0.06
     disconnected
    0.06
     grep
    0.06
    ตรวจ
    0.06
    лит
    0.06
    bable
    0.05
     обработ
    0.05
     ejec
    0.05
    سیون
    0.05
    Act Density 0.030%

    No Known Activations