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

    Neuronpedia

    INDEX
    Explanations

    hypertext links "here" or phrases with "click here"

    oai_token-act-pair · gemini-2.0-flash

    here

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BagConstraints
    -0.69
     EconPapers
    -0.69
     ་་
    -0.66
     myſelf
    -0.65
     Majefty
    -0.65
     Reſ
    -0.64
    featureID
    -0.64
     Midas
    -0.62
     ſta
    -0.60
    جوايز
    -0.60
    POSITIVE LOGITS
    endpush
    0.54
    :///
    0.44
    bigr
    0.44
    :
    0.42
     apparten
    0.39
     perpé
    0.39
    SaveChangesAsync
    0.38
    ContentAsync
    0.38
     quien
    0.38
    ReusableCell
    0.38
    Act Density 0.405%

    No Known Activations