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

    Neuronpedia

    INDEX
    Explanations

    variable names and assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vértice
    0.20
     ආකාර
    0.19
    ópez
    0.19
     Elektrokhimiya
    0.17
     môžete
    0.16
    <unused1042>
    0.16
     menimbulkan
    0.16
     ንጥረ
    0.16
     lâng
    0.15
    ichromo
    0.15
    POSITIVE LOGITS
    _
    0.39
    -
    0.25
    ed
    0.23
     =
    0.22
    Of
    0.21
    ers
    0.21
    ing
    0.20
    To
    0.20
    In
    0.20
     to
    0.19
    Act Density 0.227%

    No Known Activations