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

    Neuronpedia

    INDEX
    Explanations

    math operator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     histological
    0.46
    ্যন্তরীণ
    0.45
    ।’’
    0.44
    ।''
    0.44
    ।]
    0.42
    orragie
    0.42
     النصوص
    0.42
    〢
    0.42
     डॉक्यूमेंट्री
    0.42
    "),],
    0.40
    POSITIVE LOGITS
     {
    0.42
    acket
    0.41
           
    0.40
            
    0.40
    {
    0.39
     End
    0.39
     pass
    0.38
    mrow
    0.38
     Pass
    0.38
     T
    0.37
    Act Density 0.004%

    No Known Activations