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

    Neuronpedia

    INDEX
    Explanations

    technical explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dien
    -0.07
    єв
    -0.06
    "),↵↵
    -0.06
     Zus
    -0.06
     Milit
    -0.06
     Με
    -0.06
    ้แก
    -0.06
    #######↵
    -0.06
    .SET
    -0.06
     Written
    -0.06
    POSITIVE LOGITS
    717
    0.07
    /resources
    0.07
    109
    0.06
    alley
    0.06
    yo
    0.06
     Mutation
    0.06
    ращ
    0.06
    _exempt
    0.06
    роб
    0.06
    Exclude
    0.06
    Act Density 0.001%

    No Known Activations