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

    Neuronpedia

    INDEX
    Explanations

    formatting characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    0.76
     a
    0.61
     an
    0.56
     increased
    0.54
    the
    0.53
     informacje
    0.52
     this
    0.52
     materials
    0.52
     certaines
    0.51
     various
    0.50
    POSITIVE LOGITS
    ↵↵
    0.61
    !">
    0.52
     (>
    0.50
    ,</
    0.50
    ,))
    0.49
    !\
    0.49
    $('
    0.49
    hafte
    0.49
    !“
    0.48
    ,(
    0.48
    Act Density 2.031%

    No Known Activations