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

    Neuronpedia

    INDEX
    Explanations

    language technology and research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fath
    0.43
     tekrar
    0.40
     epiphany
    0.40
     deewana
    0.39
    wenn
    0.38
     lainnya
    0.37
     Fragen
    0.37
     distaste
    0.37
     bygone
    0.37
    iyim
    0.37
    POSITIVE LOGITS
    在
    0.50
    ជាមួយនឹង
    0.42
    從
    0.41
    根据
    0.41
    根據
    0.40
    R
    0.39
     從
    0.38
    針對
    0.38
    <0xF0>
    0.38
    ology
    0.38
    Act Density 0.034%

    No Known Activations