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

    Neuronpedia

    INDEX
    Explanations

    adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sierra
    -0.07
    angent
    -0.07
    responseData
    -0.07
    EventType
    -0.07
    スの
    -0.06
     Sunday
    -0.06
    _substr
    -0.06
     Sinai
    -0.06
    ısının
    -0.06
     Ronnie
    -0.06
    POSITIVE LOGITS
    超
    0.07
     beled
    0.07
     separ
    0.06
     băng
    0.06
     beer
    0.06
    兩
    0.06
     선택
    0.06
    -trans
    0.06
    --------
    0.06
    _depend
    0.06
    Act Density 0.348%

    No Known Activations