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

    Neuronpedia

    INDEX
    Explanations

    Acronyms "DH" or "DP"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.89
     للاسماء
    -0.85
     transfieras
    -0.82
     DH
    -0.81
    WireFormatLite
    -0.77
     autorytatywna
    -0.76
     DF
    -0.75
    WriteTagHelper
    -0.75
    ftagPool
    -0.74
    دانشنامهٔ
    -0.73
    POSITIVE LOGITS
    s
    0.61
    a
    0.58
    e
    0.56
    .
    0.51
    men
    0.50
    ,
    0.48
     paid
    0.47
    man
    0.47
     No
    0.45
    ی
    0.44
    Act Density 0.186%

    No Known Activations