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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anje
    -0.07
    encil
    -0.06
     تای
    -0.06
     Pillow
    -0.06
     Edited
    -0.06
     电
    -0.06
     trous
    -0.06
    /action
    -0.06
     saldo
    -0.06
     文
    -0.06
    POSITIVE LOGITS
    parallel
    0.07
     gallons
    0.06
    세대
    0.06
     estr
    0.06
     Parallel
    0.06
    rahim
    0.06
     определ
    0.06
    .distance
    0.06
    งหมด
    0.06
     गर
    0.06
    Act Density 0.002%

    No Known Activations