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

    Neuronpedia

    INDEX
    Explanations

    sort code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ენტი
    0.38
    itriangular
    0.38
    ínio
    0.37
    δί
    0.36
    ı
    0.36
    oto
    0.36
    iagn
    0.36
    ̽
    0.35
    ্টে
    0.35
     ठो
    0.35
    POSITIVE LOGITS
     recebe
    0.39
    অর্
    0.38
     hoops
    0.38
     Zulu
    0.38
     cafeteria
    0.37
     Distance
    0.36
     cumplir
    0.36
     Wish
    0.36
     tulips
    0.36
     Whisky
    0.36
    Act Density 0.000%

    No Known Activations