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

    Neuronpedia

    INDEX
    Explanations

    references to political motivations and social issues

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

    Follows nouns with diverse roles/functions

    np_acts-logits-general · gemini-2.0-flash

    courtesy during here

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ComVisible
    -0.78
    featureID
    -0.65
    tvguidetime
    -0.64
    #+#
    -0.59
    庁
    -0.55
     שוליים
    -0.54
    PRWEB
    -0.52
    ⓧ
    -0.51
     --;
    -0.50
    itinéraire
    -0.50
    POSITIVE LOGITS
     when
    0.65
    courtesy
    0.59
     podczas
    0.58
     lors
    0.58
     during
    0.57
     beim
    0.57
     chez
    0.56
     disini
    0.56
     courtesy
    0.56
     here
    0.55
    Act Density 1.127%

    No Known Activations