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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and words near proper nouns in the middle of sentences

    oai_token-act-pair · gemini-2.0-flash

    Kin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.53
     Stuff
    -0.52
    ++
    -0.51
    agaimana
    -0.50
    ніципалі
    -0.50
     STUFF
    -0.49
    esto
    -0.49
    tific
    -0.49
    lename
    -0.48
     FUEL
    -0.48
    POSITIVE LOGITS
    tagHelper
    0.56
    ecore
    0.54
     الاطلاع
    0.53
     estimés
    0.50
    MemoryWarning
    0.49
    Хьажоргаш
    0.48
     BOC
    0.48
    expandindo
    0.47
     copertina
    0.46
     насељу
    0.45
    Act Density 2.038%

    No Known Activations