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

    Neuronpedia

    INDEX
    Explanations

    rounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Out
    -0.57
    out
    -0.56
    Out
    -0.56
    inor
    -0.49
    athan
    -0.48
     hoạt
    -0.46
    ation
    -0.46
    umar
    -0.46
    amuk
    -0.45
     out
    -0.44
    POSITIVE LOGITS
     bezeichneter
    0.81
     насељу
    0.77
     viewType
    0.75
    +#+#
    0.72
    TestTools
    0.72
    queryInterface
    0.70
    ंदीखरीदारी
    0.69
     Infórmanos
    0.68
     betweenstory
    0.67
     ويكيپيديا
    0.66
    Act Density 1.153%

    No Known Activations