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

    Neuronpedia

    INDEX
    Explanations

    call

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ้จ
    -0.07
    台灣
    -0.06
     nech
    -0.06
     Comes
    -0.06
     agli
    -0.06
     animator
    -0.06
     Paz
    -0.06
     Beats
    -0.06
     이것
    -0.06
     canh
    -0.06
    POSITIVE LOGITS
    gift
    0.07
    NTAX
    0.07
    �
    0.07
    кадем
    0.07
    �
    0.07
    alchemy
    0.07
    ImplOptions
    0.07
    uctose
    0.06
    499
    0.06
    آن
    0.06
    Act Density 0.034%

    No Known Activations