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

    Neuronpedia

    INDEX
    Explanations

    category

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rectangles
    -0.07
    CDC
    -0.06
     зим
    -0.06
    crime
    -0.06
     бра
    -0.06
    yet
    -0.06
     nim
    -0.06
     Elm
    -0.06
     英
    -0.06
    _responses
    -0.06
    POSITIVE LOGITS
     сон
    0.07
    Resize
    0.06
     rake
    0.06
     Lazy
    0.06
     Hex
    0.06
     lover
    0.06
     companions
    0.06
    -parse
    0.06
    IFIER
    0.06
     est
    0.06
    Act Density 0.010%

    No Known Activations