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

    Neuronpedia

    INDEX
    Explanations

    statistical quantifiers, intensifiers, and words indicating large values or portions

    oai_token-act-pair · gemini-2.0-flash

    Large quantities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     onAnimation
    -0.55
     (;;)
    -0.54
    BeginContext
    -0.53
     Lippincott
    -0.53
    ftagPool
    -0.52
    indd
    -0.52
     appart
    -0.49
     RSSSF
    -0.48
    ukah
    -0.47
    TagHelper
    -0.46
    POSITIVE LOGITS
     loads
    1.40
    loads
    1.36
     Loads
    1.29
    Loads
    1.23
     load
    1.18
     tons
    1.14
     heaps
    1.13
    load
    1.10
     Tons
    1.09
     LOAD
    1.05
    Act Density 1.052%

    No Known Activations