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

    Neuronpedia

    INDEX
    Explanations

    pool

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     진행
    -0.08
     Heard
    -0.08
    进行
    -0.08
     계산
    -0.08
     законодательства
    -0.07
    .Level
    -0.07
     수행
    -0.07
     congress
    -0.07
    wb
    -0.07
     기자
    -0.07
    POSITIVE LOGITS
     bottles
    0.09
    ​�
    0.08
     bottle
    0.08
     pribadi
    0.08
    Bottle
    0.08
    Swimming
    0.08
     pills
    0.07
     pogled
    0.07
    فضل
    0.07
    estro
    0.07
    Act Density 0.009%

    No Known Activations