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

    Neuronpedia

    INDEX
    Explanations

    download/manual instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ज
    0.51
     unglaublich
    0.49
     jurusan
    0.45
    ל
    0.44
    ज्ञात
    0.44
     tumbuhan
    0.44
     academically
    0.44
     IUnary
    0.44
    ATTLE
    0.43
    AGRAM
    0.43
    POSITIVE LOGITS
     ръ
    0.51
    ματος
    0.49
     që
    0.49
     și
    0.49
    ሦ
    0.49
     كه
    0.48
     δεί
    0.48
     συμμε
    0.47
     أي
    0.46
     диза
    0.46
    Act Density 0.000%

    No Known Activations