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

    Neuronpedia

    INDEX
    Explanations

    of platforms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Computer
    0.41
    to
    0.39
     Student
    0.39
    text
    0.39
    ized
    0.38
     Text
    0.38
     Cosmetic
    0.37
     Hungarian
    0.37
     Review
    0.37
     Medical
    0.36
    POSITIVE LOGITS
    萎
    0.38
     wagons
    0.35
     pudd
    0.35
     barns
    0.35
     ferries
    0.34
     dissati
    0.34
     ovens
    0.32
     railings
    0.32
     ветра
    0.32
    膨
    0.32
    Act Density 0.000%

    No Known Activations