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

    Neuronpedia

    INDEX
    Explanations

    number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     number
    -0.69
     नंबर
    -0.65
     NUMBER
    -0.60
     Number
    -0.60
    Number
    -0.57
     gren
    -0.51
    number
    -0.51
    igram
    -0.50
     URL
    -0.50
    GOTREF
    -0.49
    POSITIVE LOGITS
    ConverterFactory
    0.69
     utafitiHapana
    0.56
     transfieras
    0.56
     rechange
    0.54
    umnos
    0.54
     hvě
    0.50
     Cari
    0.49
    ViewFeatures
    0.49
     autorytatywna
    0.49
    DockStyle
    0.49
    Act Density 0.005%

    No Known Activations