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

    Neuronpedia

    INDEX
    Explanations

    imperative commands or urgencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    always
    0.49
     always
    0.48
    in
    0.41
    appropriate
    0.40
     সর্বদা
    0.40
    badlogic
    0.40
     to
    0.39
     எப்போதும்
    0.38
    id
    0.38
    ali
    0.37
    POSITIVE LOGITS
    赶紧
    0.46
     snelheid
    0.46
     rychle
    0.45
     forthwith
    0.45
     rethink
    0.44
     conférences
    0.44
     rohkem
    0.44
     reconsider
    0.43
     pemasaran
    0.41
     segera
    0.41
    Act Density 0.125%

    No Known Activations