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

    Neuronpedia

    INDEX
    Explanations

    references to physical stunts or risky activities

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

    "climbing" or being "down"

    np_acts-logits-general · gemini-2.0-flash

    climbing and falling actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uParam
    -0.46
     redacción
    -0.44
     dredged
    -0.42
     sepol
    -0.41
    delwed
    -0.40
     comigo
    -0.39
     senhora
    -0.39
     razonable
    -0.39
    httphttps
    -0.39
     conmigo
    -0.39
    POSITIVE LOGITS
     climbing
    1.07
     climb
    0.96
    climbing
    0.88
     acrob
    0.88
     climbed
    0.88
     Climbing
    0.87
    climb
    0.85
     climbs
    0.85
    Climbing
    0.82
     climber
    0.81
    Act Density 0.245%

    No Known Activations