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

    Neuronpedia

    INDEX
    Explanations

    code snippets, instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    毉
    0.52
    Benzyl
    0.51
    Despatx
    0.49
    überküloz
    0.49
    боль
    0.49
    рость
    0.48
    の為
    0.48
    ٹنے
    0.48
     Мне
    0.47
    рети
    0.46
    POSITIVE LOGITS
    ation
    0.52
     (
    0.52
    {
    0.44
    }$
    0.43
     positive
    0.43
     Florida
    0.43
     |
    0.43
     growth
    0.41
    ných
    0.40
     Tallahassee
    0.40
    Act Density 0.008%

    No Known Activations