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

    Neuronpedia

    INDEX
    Explanations

    dedicating / dedicate to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     translateY
    0.86
     детства
    0.83
    译
    0.81
     Turismo
    0.80
     bode
    0.79
     edizione
    0.75
     Showcase
    0.73
     phase
    0.72
     uga
    0.72
     विका
    0.71
    POSITIVE LOGITS
    стре
    0.75
    elt
    0.75
    irió
    0.70
    writ
    0.66
    <h4>
    0.65
    ړو
    0.62
     સમગ્ર
    0.62
    ゎ
    0.62
    opo
    0.61
    auern
    0.60
    Act Density 0.024%

    No Known Activations