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

    Neuronpedia

    INDEX
    Explanations

    geographic or system contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    b
    0.52
    quins
    0.48
    Initially
    0.47
    izophren
    0.47
    barrier
    0.46
    Table
    0.46
     levels
    0.45
    typical
    0.45
    -;
    0.45
    AM
    0.45
    POSITIVE LOGITS
     boc
    0.50
     vías
    0.48
    '})
    0.47
    <unused34>
    0.46
     کار
    0.46
     слу
    0.45
    रात
    0.45
     любов
    0.44
    ająca
    0.44
     dane
    0.44
    Act Density 0.000%

    No Known Activations