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

    Neuronpedia

    INDEX
    Explanations

    word puzzles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ":["
    0.68
    $\
    0.66
    0.65
    ISION
    0.65
    accès
    0.65
    ENCE
    0.64
    ^{
    0.64
    ^{\
    0.63
    {$\
    0.63
    TABLE
    0.62
    POSITIVE LOGITS
     is
    0.69
     belongs
    0.66
     fordi
    0.65
     components
    0.64
     robust
    0.64
     fios
    0.63
     shell
    0.59
     komponen
    0.59
     gjør
    0.59
     ocorreu
    0.59
    Act Density 0.002%

    No Known Activations