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

    Neuronpedia

    INDEX
    Explanations

    instructions related to physical posture and yoga poses

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

    Actions involving twisting or positioning

    np_acts-logits-general · gemini-2.0-flash

    twisted outward

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '{@
    -0.52
     Messina
    -0.49
     tachy
    -0.48
    ণ
    -0.46
     Healey
    -0.46
     Subsystem
    -0.45
     Corinth
    -0.45
     Wund
    -0.44
     teasing
    -0.44
    makeConstraints
    -0.44
    POSITIVE LOGITS
     kasarigan
    0.70
     holdt
    0.60
     plastiques
    0.59
     posizione
    0.59
     fermés
    0.58
    jsonwebtoken
    0.56
     otomatig
    0.56
    Stayed
    0.56
     cérami
    0.55
    apnews
    0.54
    Act Density 0.249%

    No Known Activations