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

    Neuronpedia

    INDEX
    Explanations

    Lifeline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     اربعه
    0.83
     sıral
    0.80
    zeichnis
    0.79
    Alchemy
    0.78
    ಭಾ
    0.77
    ulte
    0.75
    closes
    0.75
    스럽
    0.74
    ણા
    0.74
    atz
    0.73
    POSITIVE LOGITS
     У
    0.96
     pink
    0.86
    muc
    0.86
     данным
    0.85
     این
    0.83
     classical
    0.83
    white
    0.83
    health
    0.83
    voice
    0.81
     white
    0.81
    Act Density 0.019%

    No Known Activations