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

    Neuronpedia

    INDEX
    Explanations

    functions with arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مباشرة
    0.44
    हेही
    0.41
    Ꮰ
    0.40
    ीजन
    0.40
    रेन
    0.40
    बास
    0.39
    રિક
    0.37
     ஊற
    0.37
    getSelected
    0.36
     আবরণ
    0.36
    POSITIVE LOGITS
     arguments
    0.63
     arg
    0.57
     argument
    0.57
     Argument
    0.56
    Arg
    0.55
     Arg
    0.54
     Arguments
    0.54
     аргу
    0.53
    Argument
    0.52
     args
    0.50
    Act Density 0.001%

    No Known Activations