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

    Neuronpedia

    INDEX
    Explanations

    statements regarding political accountability and criticisms of leadership

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

    expressions of belief or reaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Билгалдахарш
    -0.73
    httphttps
    -0.67
    astéroïdes
    -0.66
    featureID
    -0.64
     houſe
    -0.61
    OGND
    -0.61
     poffible
    -0.61
     ſein
    -0.61
    UnknownFieldSet
    -0.60
     Houſe
    -0.60
    POSITIVE LOGITS
    <eos>
    0.38
     .
    0.34
    ↵
    0.34
    ress
    0.33
    </h2>
    0.33
    .
    0.33
    -
    0.32
     shared
    0.32
    ,
    0.32
     (
    0.31
    Act Density 0.136%

    No Known Activations