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

    Neuronpedia

    INDEX
    Explanations

    references to organizations and their actions in a legal or regulatory context

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

    defend or respond

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumi
    -0.47
     @"/
    -0.40
     naveg
    -0.40
     ruines
    -0.38
     reik
    -0.37
    OBSERV
    -0.37
    EROUS
    -0.36
     cardin
    -0.36
     semn
    -0.36
    </tfoot>
    -0.36
    POSITIVE LOGITS
     defended
    1.86
     defends
    1.76
     defend
    1.60
     defending
    1.53
     defense
    1.47
     defence
    1.40
     defenses
    1.33
     défend
    1.32
     defenders
    1.32
     défendre
    1.24
    Act Density 0.107%

    No Known Activations