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

    Neuronpedia

    INDEX
    Explanations

    definitions and declarations of classes and functions in code

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

    Python code definition start

    np_acts-logits-general · gemini-2.0-flash

    python function definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Shakspeare
    -0.92
     itſelf
    -0.90
     doubtnut
    -0.90
     himſelf
    -0.73
     themſelves
    -0.72
     Efq
    -0.72
     Persians
    -0.72
     ſeveral
    -0.71
     photolibrary
    -0.70
     Majefty
    -0.70
    POSITIVE LOGITS
     __
    1.25
     _
    1.07
     my
    0.82
     get
    0.78
    MigrationBuilder
    0.78
     cal
    0.74
     CreateTagHelper
    0.73
     def
    0.72
    ÓS
    0.70
     f
    0.70
    Act Density 0.050%

    No Known Activations