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

    Neuronpedia

    INDEX
    Explanations

    collection after a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diverse
    0.81
     varied
    0.79
     diverso
    0.77
     Diverse
    0.73
    ভেদ
    0.72
     diversa
    0.70
    diverse
    0.70
    訫
    0.69
     diversified
    0.68
     diversi
    0.67
    POSITIVE LOGITS
     bunch
    1.79
     array
    1.76
     pile
    1.75
     slew
    1.73
     collection
    1.71
     stream
    1.71
     flurry
    1.69
     bevy
    1.67
     barrage
    1.64
     stack
    1.62
    Act Density 0.428%

    No Known Activations