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

    Neuronpedia

    INDEX
    Explanations

    latex commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     refunds
    0.50
     franchisees
    0.48
    ڑوں
    0.47
    వ్వు
    0.46
     transacción
    0.46
     onboarding
    0.46
     vinaig
    0.46
     ferries
    0.46
    ूरत
    0.45
     scooters
    0.45
    POSITIVE LOGITS
    {\
    0.73
     \
    0.67
    }\
    0.66
     {\
    0.65
    %\
    0.64
    \
    0.64
     arXiv
    0.63
    $\
    0.62
    <0x0D>
    0.60
    {
    0.57
    Act Density 0.001%

    No Known Activations