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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fully
    -0.08
    剩
    -0.07
    簡
    -0.07
     favourable
    -0.06
     architects
    -0.06
    感
    -0.06
    -care
    -0.06
    �
    -0.06
    Correct
    -0.06
    節
    -0.06
    POSITIVE LOGITS
    artin
    0.08
     برابر
    0.07
     edildi
    0.07
    ίλ
    0.06
     dues
    0.06
     Ihrer
    0.06
    Oi
    0.06
    _serializer
    0.06
     Ler
    0.06
     Firearms
    0.06
    Act Density 0.053%

    No Known Activations