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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     maybe
    0.61
     possibly
    0.58
     Maybe
    0.53
     möglicherweise
    0.51
     Possibly
    0.50
     ensures
    0.50
     perhaps
    0.50
    possibly
    0.48
     Ensures
    0.47
     vielleicht
    0.46
    POSITIVE LOGITS
     buvo
    1.21
     kellett
    1.17
     była
    1.13
     didn
    1.12
     konnte
    1.12
     είχε
    1.12
     did
    1.11
     konnten
    1.08
     وكانت
    1.08
     had
    1.07
    Act Density 0.005%

    No Known Activations