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

    Neuronpedia

    INDEX
    Explanations

    don't / didn't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    0.58
     you
    0.54
    '
    0.50
    보
    0.50
    6
    0.49
    -
    0.49
    ON
    0.48
     screwdriver
    0.47
     notary
    0.46
     router
    0.46
    POSITIVE LOGITS
    h
    0.58
    b
    0.46
    v
    0.46
    0.44
    esi
    0.43
    lara
    0.43
    含ま
    0.41
    اي
    0.41
     вследствие
    0.40
    ane
    0.40
    Act Density 0.092%

    No Known Activations