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

    Neuronpedia

    INDEX
    Explanations

    multilingual text snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     River
    0.52
    app
    0.49
    e
    0.48
     Trading
    0.48
     Legend
    0.48
    ной
    0.47
     Ser
    0.47
    1
    0.47
     Functional
    0.47
     Cathedral
    0.46
    POSITIVE LOGITS
    သမ
    0.52
     பயன்படுத்து
    0.50
     וי
    0.49
     superficies
    0.47
    infodisc
    0.46
    CreateWall
    0.46
    خواندن
    0.46
     綿
    0.46
     społ
    0.45
    時は
    0.44
    Act Density 0.000%

    No Known Activations