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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions with variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ->
    1.00
    YOUR
    0.99
     →
    0.97
     -->
    0.94
     tuo
    0.93
     あなた
    0.92
     =>
    0.92
     =
    0.89
     YOUR
    0.89
     ≠
    0.89
    POSITIVE LOGITS
    ^{\
    1.07
    $
    0.95
    \%$
    0.89
    }^{\
    0.88
     \%$
    0.87
    ^{
    0.82
     its
    0.82
    ]$,
    0.80
    _{\
    0.77
    \
    0.77
    Act Density 0.313%

    No Known Activations