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

    Neuronpedia

    INDEX
    Explanations

    torque, moment, green grass

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    మిక
    0.42
     Aucun
    0.40
     Пло
    0.40
    allyl
    0.40
     중심
    0.40
    тельным
    0.39
    畈
    0.38
    worthy
    0.38
    টসঅ্যাপ
    0.38
    ობა
    0.37
    POSITIVE LOGITS
     tors
    0.51
     tor
    0.50
     Torque
    0.47
     torque
    0.46
     kom
    0.45
    tor
    0.42
    torque
    0.41
    kom
    0.37
    sos
    0.37
     moment
    0.36
    Act Density 0.000%

    No Known Activations