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

    Neuronpedia

    INDEX
    Explanations

    ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.99
    ,
    0.98
     to
    0.97
    :
    0.84
     is
    0.83
    !
    0.82
     at
    0.81
    .
    0.81
     be
    0.80
     on
    0.79
    POSITIVE LOGITS
    también
    0.85
    嵃
    0.76
    <unused336>
    0.75
     trueMap
    0.74
    髗
    0.72
     givenChar
    0.71
    誢
    0.70
    <unused1030>
    0.70
    ának
    0.69
     bottlene
    0.69
    Act Density 0.000%

    No Known Activations