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

    Neuronpedia

    INDEX
    Explanations

    AI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    exc
    -0.06
     :
↵
    -0.06
     transporte
    -0.06
    -temp
    -0.06
    воз
    -0.06
    .Nil
    -0.06
    ��
    -0.06
     conced
    -0.06
    (conv
    -0.06
     druhý
    -0.06
    POSITIVE LOGITS
    AI
    0.11
    ai
    0.10
    ail
    0.07
    akin
    0.07
    _API
    0.07
    HERE
    0.06
     Savage
    0.06
    sey
    0.06
     trình
    0.06
    ар
    0.06
    Act Density 0.004%

    No Known Activations