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

    Neuronpedia

    INDEX
    Explanations

    references to comparisons and contrasting elements in descriptions

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

    describing things emotionally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UpInside
    -0.48
    XmlAccessorType
    -0.48
     utafitiHapana
    -0.47
    spesies
    -0.47
     cliquez
    -0.46
    पया
    -0.45
    jména
    -0.44
    hånd
    -0.44
    Tikang
    -0.44
    ėmis
    -0.44
    POSITIVE LOGITS
    EDEFAULT
    0.42
     Mol
    0.41
     Италијани
    0.39
     Rot
    0.39
     NC
    0.37
     Савезне
    0.36
    isim
    0.36
     astronomer
    0.35
     Coll
    0.35
     infant
    0.35
    Act Density 0.025%

    No Known Activations