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

    Neuronpedia

    INDEX
    Explanations

    deontology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kem
    0.42
     Kem
    0.41
     kem
    0.40
    Wheel
    0.39
    пита
    0.37
    sd
    0.37
    wheel
    0.37
    ash
    0.36
    ων
    0.36
    pin
    0.36
    POSITIVE LOGITS
     monopolies
    0.46
     Voss
    0.45
    ทรง
    0.39
     benc
    0.38
     Barlow
    0.38
    ْت
    0.37
     datar
    0.37
     antitrust
    0.36
     Carmine
    0.36
     Creates
    0.35
    Act Density 0.002%

    No Known Activations