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

    Neuronpedia

    INDEX
    Explanations

    types of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    0.46
     lodging
    0.44
     disclosures
    0.44
     distributions
    0.43
    6
    0.43
     aces
    0.42
     hydrogenation
    0.41
     weekend
    0.40
     locations
    0.39
     averaging
    0.39
    POSITIVE LOGITS
    ický
    0.48
     சிறிது
    0.47
    ிக்
    0.46
     quedó
    0.46
    ろしく
    0.44
    悩
    0.43
    enade
    0.43
     고민
    0.43
     Joaquín
    0.43
     AppMethodBeat
    0.43
    Act Density 0.019%

    No Known Activations