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

    Neuronpedia

    INDEX
    Explanations

    Various news stories

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disse
    -0.08
                
↵
    -0.07
    长得
    -0.07
    ência
    -0.07
    Distance
    -0.07
     QB
    -0.07
    actices
    -0.07
     информ
    -0.07
     dec
    -0.07
    leich
    -0.06
    POSITIVE LOGITS
     stake
    0.07
     handful
    0.07
    甗
    0.07
    _dummy
    0.07
    пол
    0.07
     Barcode
    0.07
    mentor
    0.07
    _Result
    0.07
     Kart
    0.07
    oader
    0.06
    Act Density 0.117%

    No Known Activations