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

    Neuronpedia

    INDEX
    Explanations

    language handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     awful
    0.91
     dreadful
    0.84
     terrible
    0.81
     horrible
    0.80
     punishable
    0.73
    ultures
    0.72
     rendah
    0.71
     대로
    0.71
     framework
    0.71
    pperware
    0.70
    POSITIVE LOGITS
     Foto
    0.79
     पहलू
    0.70
     সক
    0.70
     Photos
    0.68
     Fot
    0.68
     Recommendations
    0.66
     Tipps
    0.65
     Фото
    0.65
     quis
    0.65
    Recipe
    0.64
    Act Density 0.000%

    No Known Activations