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

    Neuronpedia

    INDEX
    Explanations

    Code and uncommon words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SharedCtor
    -0.54
     Савезне
    -0.48
    Lähteet
    -0.40
     חיצוניים
    -0.35
     MenuView
    -0.34
     defaultstate
    -0.33
     estekak
    -0.33
     sounded
    -0.32
    transcription
    -0.32
     হয়
    -0.31
    POSITIVE LOGITS
     CURIAM
    0.66
    WAUKEE
    0.62
     ADE
    0.62
     Endor
    0.61
    FET
    0.60
    bootstrapcdn
    0.59
     незавершена
    0.58
    CloseOperation
    0.57
    makeConstraints
    0.57
    lovakia
    0.57
    Act Density 0.000%

    No Known Activations