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

    Neuronpedia

    INDEX
    Explanations

    segments of code

    oai_token-act-pair · gemini-2.0-flash

    diverse patterns of text or error messages

    np_token-act-pair-logits · gpt-4o-mini

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    principalTable
    -0.85
    AddTagHelper
    -0.84
     Efq
    -0.83
     myſelf
    -0.83
    tagHelperRunner
    -0.81
     autorytatywna
    -0.79
    StructEnd
    -0.77
     againſt
    -0.75
     itſelf
    -0.74
     neceff
    -0.74
    POSITIVE LOGITS
    uma
    0.37
     E
    0.37
     ma
    0.36
    Архівовано
    0.36
     min
    0.36
    tamaan
    0.36
     art
    0.35
     I
    0.35
     on
    0.34
     bi
    0.34
    Act Density 0.247%

    No Known Activations