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

    Neuronpedia

    INDEX
    Explanations

    verbs and action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㓩
    0.42
    ObjectTemp
    0.41
     whe
    0.39
     item
    0.38
     場合
    0.38
     विषया
    0.38
     panini
    0.37
     অব
    0.37
     सम्मान
    0.37
     lengthening
    0.37
    POSITIVE LOGITS
     verbs
    1.75
     verb
    1.72
    Verb
    1.41
     Verb
    1.41
    verb
    1.38
    verbs
    1.35
     verbo
    1.26
     action
    0.84
    verbosity
    0.84
    Action
    0.82
    Act Density 0.125%

    No Known Activations