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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    oai_token-act-pair · gemini-2.0-flash

    non-standard characters and formatting

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

    code context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ar
    -0.61
     pa
    -0.59
     
    -0.59
     Pa
    -0.57
     ch
    -0.57
     par
    -0.56
     t
    -0.56
     T
    -0.56
     CH
    -0.53
     Ch
    -0.52
    POSITIVE LOGITS
     snippetHide
    1.44
     '\\;'
    1.20
    tvguidetime
    1.16
    1.13
    MigrationBuilder
    1.13
    kháu
    1.12
    ########.
    1.09
    AsUp
    1.09
    #+#
    1.08
    expandindo
    1.08
    Act Density 2.273%

    No Known Activations