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

    Neuronpedia

    INDEX
    Explanations

    my relationship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AQP
    0.81
     Circuit
    0.81
     freely
    0.75
     authorized
    0.75
     Leah
    0.73
    AAP
    0.73
     Authorized
    0.71
     David
    0.70
     Mechanics
    0.70
     wyróż
    0.69
    POSITIVE LOGITS
     whatever
    1.04
     coworkers
    1.01
    whatever
    0.96
     coworker
    0.89
     ...]
    0.89
    Whatever
    0.86
     roommates
    0.84
     roommate
    0.80
     argumentative
    0.80
    เพื่อน
    0.79
    Act Density 0.000%

    No Known Activations