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

    Neuronpedia

    INDEX
    Explanations

    me to / let's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jadi
    0.89
    ril
    0.80
    rün
    0.77
     vivid
    0.71
     soff
    0.70
     nostra
    0.68
    lern
    0.67
     admission
    0.66
     magnificent
    0.66
     debut
    0.65
    POSITIVE LOGITS
     أو
    0.96
     или
    0.95
     kelly
    0.93
     Assignment
    0.89
    attempts
    0.87
     또는
    0.86
    или
    0.86
    <unused2049>
    0.86
    または
    0.84
     asserts
    0.84
    Act Density 0.196%

    No Known Activations