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

    Neuronpedia

    INDEX
    Explanations

    F-words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    गुप्त
    0.40
    ەش
    0.39
     있다
    0.38
     chiral
    0.38
    octrl
    0.38
    ემის
    0.38
    imwrite
    0.38
    sommets
    0.37
    वाती
    0.37
    hearted
    0.36
    POSITIVE LOGITS
     F
    0.89
     f
    0.73
    F
    0.73
     ফ
    0.68
    <0x86>
    0.63
    f
    0.63
     फ
    0.62
    avorable
    0.62
     ഫ
    0.57
     Fahrenheit
    0.57
    Act Density 0.068%

    No Known Activations