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

    Neuronpedia

    INDEX
    Explanations

    responsibility shifts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    saver
    0.40
    rs
    0.37
    lesque
    0.36
    ått
    0.36
    fulfill
    0.36
    ೈಸ
    0.35
    aston
    0.35
    ack
    0.35
    cm
    0.35
    Loading
    0.35
    POSITIVE LOGITS
     Used
    0.43
     प्रोटो
    0.41
     Press
    0.40
     getIntent
    0.39
     Synthetic
    0.39
     ‘‘
    0.39
     kreeg
    0.39
     utilisé
    0.38
     stron
    0.38
     ఎన్ని
    0.38
    Act Density 0.000%

    No Known Activations