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

    Neuronpedia

    INDEX
    Explanations

    explaining complex concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gegevens
    0.80
    estal
    0.79
     каждая
    0.79
     impuestos
    0.78
    ovalent
    0.76
     дерев
    0.76
    OCCO
    0.74
     грузо
    0.73
     аллер
    0.73
     другая
    0.73
    POSITIVE LOGITS
    يدك
    0.75
    ف
    0.74
    يد
    0.71
    الى
    0.70
    ير
    0.69
    ബി
    0.69
     prvi
    0.69
    看来
    0.68
     latest
    0.68
    띈
    0.67
    Act Density 0.000%

    No Known Activations