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

    Neuronpedia

    INDEX
    Explanations

    terms associated with significant weight, particularly in relation to materials or actions

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

    following "heavy"

    np_acts-logits-general · gemini-2.0-flash

    heavy followed by related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hochspringen
    -0.65
    PreferredItem
    -0.63
    __*/
    -0.56
    soever
    -0.55
    XmlAccessorType
    -0.53
    uette
    -0.53
    :][
    -0.52
    :✨
    -0.52
    alış
    -0.51
     trustees
    -0.51
    POSITIVE LOGITS
     Heavy
    1.27
    Heavy
    1.26
     heavy
    1.24
     HEAVY
    1.19
    heavy
    1.18
    heav
    1.18
    weights
    1.15
     duty
    1.08
    duty
    1.07
     heaviest
    1.02
    Act Density 0.047%

    No Known Activations