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

    Neuronpedia

    INDEX
    Explanations

    clustering algorithms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     satış
    -0.07
     okuy
    -0.06
    edor
    -0.06
    息
    -0.06
    ajan
    -0.06
    abras
    -0.06
     Copyright
    -0.06
    INDOW
    -0.06
    ucha
    -0.06
    Cloud
    -0.06
    POSITIVE LOGITS
     bis
    0.06
     alias
    0.06
    .avg
    0.06
     동일
    0.06
    適
    0.06
    είς
    0.06
     अप
    0.06
     nghĩ
    0.06
     cater
    0.06
     taps
    0.06
    Act Density 0.016%

    No Known Activations