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

    Neuronpedia

    INDEX
    Explanations

    every, all, everything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused2175>
    0.73
     veľmi
    0.63
    డం
    0.62
     soud
    0.61
     worms
    0.61
     অনেকেই
    0.61
     dout
    0.60
     môi
    0.59
     konusunda
    0.59
     muy
    0.57
    POSITIVE LOGITS
    this
    0.88
    that
    0.68
    in
    0.66
    these
    0.64
    the
    0.63
    his
    0.63
    この
    0.63
     excepto
    0.59
    as
    0.57
    there
    0.57
    Act Density 0.592%

    No Known Activations