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

    Neuronpedia

    INDEX
    Explanations

    root

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sofas
    -0.07
    ча
    -0.06
     шир
    -0.06
    _DIP
    -0.06
    .slot
    -0.06
     vulgar
    -0.06
    夕
    -0.05
     resized
    -0.05
     african
    -0.05
    scopy
    -0.05
    POSITIVE LOGITS
    _listing
    0.08
    anguard
    0.08
    -cut
    0.08
     Vanguard
    0.08
     Medicaid
    0.08
     QR
    0.07
    '$
    0.07
     Booker
    0.07
    ündeki
    0.07
     cut
    0.07
    Act Density 0.008%

    No Known Activations