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

    Neuronpedia

    INDEX
    Explanations

    autonomous vehicles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    against
    0.47
     humain
    0.45
    လဲ
    0.44
     AGAINST
    0.44
    Placed
    0.44
     Against
    0.44
    کو
    0.44
    నాన్ని
    0.43
     இன்னும்
    0.42
     melawan
    0.42
    POSITIVE LOGITS
     then
    0.43
    Then
    0.39
     отзы
    0.39
    Rendering
    0.38
    then
    0.38
    认可
    0.37
    以及
    0.37
    Slow
    0.36
    Process
    0.35
    Rais
    0.35
    Act Density 0.001%

    No Known Activations