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

    Neuronpedia

    INDEX
    Explanations

    formula definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $=
    0.41
     principal
    0.40
    _='
    0.39
     described
    0.39
     proposed
    0.39
    :
    0.38
     '_
    0.38
     rotating
    0.37
    =
    0.36
    ={
    0.36
    POSITIVE LOGITS
     Looks
    0.52
     выглядит
    0.52
     looks
    0.47
     wygląda
    0.47
    looks
    0.45
    Looks
    0.45
     associés
    0.44
    되면
    0.44
     ervan
    0.43
    associated
    0.42
    Act Density 0.001%

    No Known Activations