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

    Neuronpedia

    INDEX
    Explanations

    conditions for necessity or certainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Maybe
    0.86
    Maybe
    0.86
     kanske
    0.85
     maybe
    0.84
     perhaps
    0.80
     vielleicht
    0.79
    maybe
    0.79
     Vielleicht
    0.78
     Perhaps
    0.76
     mungkin
    0.75
    POSITIVE LOGITS
     almeno
    0.70
    至少
    0.66
     atleast
    0.64
    少なくとも
    0.61
     someplace
    0.57
     nějak
    0.54
     nontrivial
    0.54
     mindestens
    0.54
     somewhere
    0.52
    तमंद
    0.51
    Act Density 0.005%

    No Known Activations