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

    Neuronpedia

    INDEX
    Explanations

    references to multiple or various items

    oai_token-act-pair · gemini-2.0-flash

    several

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     several
    -1.52
    several
    -1.42
    Several
    -1.36
     Several
    -1.30
     plusieurs
    -1.08
     varios
    -0.97
     numerous
    -0.94
     mehreren
    -0.94
     várias
    -0.94
     multiple
    -0.92
    POSITIVE LOGITS
     CreateTagHelper
    0.97
    
    0.71
    TestingModule
    0.71
    tagext
    0.69
    ergies
    0.69
    findpost
    0.68
    protoimpl
    0.67
    troppo
    0.65
    anyahu
    0.64
     cref
    0.60
    Act Density 1.771%

    No Known Activations