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

    Neuronpedia

    INDEX
    Explanations

    software

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     limelight
    0.71
     waistband
    0.71
     odometer
    0.70
     accelerometer
    0.67
    ຂໍ້ມ
    0.67
     slowing
    0.67
    uroy
    0.67
     rectangular
    0.67
     tulle
    0.66
     neurological
    0.66
    POSITIVE LOGITS
    Politics
    0.50
    ве
    0.47
    Los
    0.47
    Terr
    0.47
    Side
    0.46
    Nut
    0.46
     Politics
    0.45
    Der
    0.45
    Division
    0.45
    Problem
    0.44
    Act Density 0.005%

    No Known Activations