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

    Neuronpedia

    INDEX
    Explanations

    the right place

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Prefer
    0.43
     Prefer
    0.41
    പ്പ
    0.40
    ളു
    0.40
    гает
    0.39
    並
    0.39
     daž
    0.38
    ifères
    0.38
     perdida
    0.38
     preferring
    0.38
    POSITIVE LOGITS
    हमने
    0.40
     हमने
    0.40
     conoce
    0.39
     Grossman
    0.39
     reunited
    0.38
    chern
    0.38
     тепер
    0.38
     теперь
    0.37
     Advocacy
    0.37
     Adv
    0.37
    Act Density 0.002%

    No Known Activations