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

    Neuronpedia

    INDEX
    Explanations

    code, data structures, and science

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Moż
    1.29
    ]={
    1.23
    дер
    1.20
    1.20
     Jalan
    1.20
     commemoration
    1.18
    মেঘ
    1.17
    amese
    1.17
    সের
    1.17
    вото
    1.17
    POSITIVE LOGITS
    tare
    1.00
     préd
    0.94
    ంట్
    0.93
     αν
    0.93
    objet
    0.88
     απε
    0.86
     ne
    0.86
    ocyanate
    0.85
     objet
    0.84
    たん
    0.84
    Act Density 0.000%

    No Known Activations