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

    Neuronpedia

    INDEX
    Explanations

    words indicating movement or spatial positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    away, up, fire, ground, working, invented

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.66
    -0.64
    Atsauces
    -0.60
     kasarigan
    -0.59
     typelib
    -0.58
     voran
    -0.58
    něž
    -0.57
    RTEX
    -0.57
     burgeoning
    -0.56
    modelBuilder
    -0.56
    POSITIVE LOGITS
     airplanes
    0.45
    FUCK
    0.45
     everybody
    0.44
     Anſ
    0.43
     stuff
    0.43
     airplane
    0.42
     spion
    0.41
     Inſ
    0.41
     STUFF
    0.40
    Everybody
    0.40
    Act Density 0.067%

    No Known Activations