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

    Neuronpedia

    INDEX
    Explanations

    references to people and organizations related to various contexts

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

    Plural nouns

    np_acts-logits-general · gemini-2.0-flash

    biggest own group entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.63
     frågan
    -0.57
    קישורים
    -0.54
    chenkt
    -0.54
    AnchorStyles
    -0.53
     autorytatywna
    -0.52
     juos
    -0.52
     torchvision
    -0.51
     skolan
    -0.50
     varandra
    -0.50
    POSITIVE LOGITS
     own
    1.07
     biggest
    0.81
     entire
    0.78
     final
    0.75
     ability
    0.71
     sole
    0.70
     "}";
    0.69
     main
    0.69
     greatest
    0.69
     inner
    0.68
    Act Density 0.252%

    No Known Activations