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

    Neuronpedia

    INDEX
    Explanations

    repeat and elaborate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    It
    0.53
     is
    0.51
     has
    0.50
    And
    0.49
     gives
    0.49
    The
    0.47
     gibt
    0.46
     ใช้
    0.46
    Another
    0.46
    You
    0.46
    POSITIVE LOGITS
    rog
    0.50
    rogens
    0.49
     whatnot
    0.45
     frankly
    0.43
     hatta
    0.43
     therefore
    0.41
     improvisation
    0.40
     minimalist
    0.39
     espionage
    0.39
     somit
    0.39
    Act Density 1.517%

    No Known Activations