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

    Neuronpedia

    INDEX
    Explanations

    Princeton University

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x80>
    0.92
    (
    0.86
    begin
    0.78
    _
    0.76
    -
    0.71
    ри
    0.70
    і
    0.69
    це
    0.68
    与
    0.66
    ти
    0.66
    POSITIVE LOGITS
     Senegal
    0.67
     Segunda
    0.67
     alleys
    0.66
     the
    0.66
     Warhammer
    0.64
    ipu
    0.63
     Jamestown
    0.63
     Reformed
    0.63
    obia
    0.62
     Second
    0.61
    Act Density 0.000%

    No Known Activations