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

    Neuronpedia

    INDEX
    Explanations

    websites, charting, accessing resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sk
    0.49
     Aut
    0.46
     Aff
    0.45
     Euro
    0.45
     Indus
    0.45
    Bar
    0.44
     DeS
    0.43
     an
    0.43
    Z
    0.43
     Challenge
    0.42
    POSITIVE LOGITS
    ushes
    0.47
     करीना
    0.46
    ίων
    0.46
    pyridine
    0.46
    пы
    0.45
     पार्षद
    0.45
    atán
    0.45
    ларын
    0.44
    🍰
    0.44
    TempVal
    0.44
    Act Density 0.002%

    No Known Activations