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

    Neuronpedia

    INDEX
    Explanations

    references to coding, thank you and IT related pronouns in the context of helping behavior

    oai_token-act-pair · gemini-2.0-flash

    it

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.72
    aarrggbb
    -0.66
    EndGlobalSection
    -0.65
    MigrationBuilder
    -0.59
    <bos>
    -0.53
    enumi
    -0.52
    tagext
    -0.51
    ardians
    -0.50
     purport
    -0.50
    vaného
    -0.50
    POSITIVE LOGITS
    Hentet
    0.52
    ########.
    0.51
     שוליים
    0.51
    JScrollPane
    0.50
    ]`
    0.49
    DataAnnotations
    0.47
    ⓧ
    0.47
    ApJ
    0.47
    NTSTATUS
    0.44
    ̍t
    0.44
    Act Density 0.753%

    No Known Activations