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

    Neuronpedia

    INDEX
    Explanations

    actions associated with destruction or collapse

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

    Movement downwards (falling, knocking down)

    np_acts-logits-general · gemini-2.0-flash

    fall and knock down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.74
     propOrder
    -0.66
    الحياه
    -0.65
    -0.64
    OGND
    -0.61
     simplifié
    -0.60
     ModelExpression
    -0.60
     Réponses
    -0.59
     artem
    -0.54
     FANDOM
    -0.53
    POSITIVE LOGITS
     fall
    1.56
     falling
    1.47
     down
    1.43
     fell
    1.38
    fall
    1.37
     fallen
    1.31
    FALL
    1.30
     falls
    1.30
    down
    1.28
     Fall
    1.27
    Act Density 0.196%

    No Known Activations