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

    Neuronpedia

    INDEX
    Explanations

    6 followed by 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     momentum
    0.60
     limit
    0.59
     distinct
    0.53
     supers
    0.53
     habit
    0.52
     internal
    0.52
     mock
    0.51
     specific
    0.51
     initial
    0.51
     temporary
    0.51
    POSITIVE LOGITS
    ("|"+"
    0.69
    itabbo
    0.67
    kében
    0.67
    áról
    0.66
    astaan
    0.65
    <unused196>
    0.65
    轱
    0.64
    <unused1933>
    0.64
    遭受
    0.63
     ۋە
    0.63
    Act Density 0.188%

    No Known Activations