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

    Neuronpedia

    INDEX
    Explanations

    detailed step by step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bottles
    1.25
    ০০
    1.24
    brak
    1.23
    ب
    1.17
    றிய
    1.17
    itive
    1.14
    hall
    1.13
    विष्ट
    1.13
    bonding
    1.11
     shelves
    1.11
    POSITIVE LOGITS
    Bien
    1.17
    Precio
    1.16
     opções
    1.16
    Опера
    1.15
    Deux
    1.14
    urium
    1.13
    Съ
    1.11
    Curso
    1.09
    ète
    1.08
     Cette
    1.08
    Act Density 0.000%

    No Known Activations