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

    Neuronpedia

    INDEX
    Explanations

    `&` or `(&` and `)&`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cium
    0.49
    oconut
    0.44
     kayaking
    0.44
     Pelham
    0.44
     photochemical
    0.43
     त्याची
    0.42
     आभार
    0.41
    infused
    0.41
    azote
    0.41
     व्हाउचर
    0.41
    POSITIVE LOGITS
    (&
    1.39
     &
    1.09
    >(&
    1.05
     &(
    1.02
    )(&
    1.00
     (&
    0.97
    ,&
    0.92
    =&
    0.92
    &
    0.91
    ",&
    0.86
    Act Density 0.015%

    No Known Activations