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

    Neuronpedia

    INDEX
    Explanations

    references to physical laws and principles

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

    governing laws and forces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ChildScrollView
    -0.85
     queſta
    -0.67
    ſicht
    -0.65
    UnsafeEnabled
    -0.64
     surla
    -0.63
    OrBuilder
    -0.63
    AnchorTagHelper
    -0.62
    MessageTagHelper
    -0.61
     müſſen
    -0.60
    omeness
    -0.60
    POSITIVE LOGITS
     governing
    0.38
     laws
    0.36
     leyes
    0.34
     forces
    0.32
     rules
    0.30
     force
    0.30
     regler
    0.29
    rules
    0.28
     planet
    0.28
     lois
    0.28
    Act Density 0.023%

    No Known Activations