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

    Neuronpedia

    INDEX
    Explanations

    motor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     offences
    -0.08
     clique
    -0.08
     friendships
    -0.08
     offence
    -0.07
    aviar
    -0.07
     contin
    -0.07
     Inhalte
    -0.07
     enforced
    -0.07
     offense
    -0.07
     crian
    -0.07
    POSITIVE LOGITS
     torque
    0.11
     Torque
    0.10
    Torque
    0.10
     الكهربائية
    0.09
     baja
    0.09
     eléctrica
    0.09
     électrique
    0.09
     listrik
    0.09
    /storage
    0.09
     motors
    0.08
    Act Density 0.010%

    No Known Activations