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

    Neuronpedia

    INDEX
    Explanations

    references to political candidates and related terminology

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

    followed by job titles or affiliations

    np_acts-logits-general · gemini-2.0-flash

    roles and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.78
    SharedDtor
    -0.71
     InputDecoration
    -0.70
    RegressionTest
    -0.68
     Réponses
    -0.67
     الحره
    -0.67
     يتيمه
    -0.67
    ]-->
    -0.65
    XmlAccessorType
    -0.64
     gynhyrchwyd
    -0.64
    POSITIVE LOGITS
     ört
    0.54
     féminine
    0.50
    oucí
    0.49
    chila
    0.48
     occasionally
    0.47
     extérieurs
    0.47
    μένη
    0.46
     destinées
    0.45
     Frazier
    0.45
    cuado
    0.45
    Act Density 0.411%

    No Known Activations