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

    Neuronpedia

    INDEX
    Explanations

    equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ịch
    -0.08
     업무
    -0.08
    _docs
    -0.08
     professionals
    -0.07
    ataloader
    -0.07
     understandably
    -0.07
    -awareness
    -0.07
     oldukça
    -0.07
     πολι
    -0.07
    炎
    -0.07
    POSITIVE LOGITS
     Polynomial
    0.11
     polynomial
    0.11
    Polynomial
    0.10
    ynomial
    0.09
    चा
    0.08
     kth
    0.08
     पदार्थ
    0.08
     término
    0.08
     uncomplicated
    0.08
     ith
    0.08
    Act Density 0.017%

    No Known Activations