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

    Neuronpedia

    INDEX
    Explanations

    clause

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Aner
    -0.08
    انا
    -0.08
     Assembly
    -0.08
     Entrance
    -0.08
    وري
    -0.08
    assembl
    -0.07
     Techniques
    -0.07
     Sciences
    -0.07
     Increment
    -0.07
     nant
    -0.07
    POSITIVE LOGITS
     stipulated
    0.10
     varsa
    0.09
    했던
    0.09
    'habitude
    0.09
    规定
    0.08
     установлен
    0.08
    ிருந்த
    0.08
     vows
    0.08
     договора
    0.08
    合同
    0.08
    Act Density 0.047%

    No Known Activations