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

    Neuronpedia

    INDEX
    Explanations

    ** ** :

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ot
    0.52
    lists
    0.51
    를
    0.47
    lista
    0.46
    enriched
    0.45
     employment
    0.45
    lisher
    0.44
    list
    0.43
     फ़ोन
    0.43
    dated
    0.43
    POSITIVE LOGITS
    ازت
    0.45
     schneller
    0.44
     entweder
    0.44
     стре
    0.44
     stessi
    0.43
    ణ
    0.43
    逭
    0.42
     стадии
    0.42
     Bxg
    0.42
    μπο
    0.42
    Act Density 0.001%

    No Known Activations