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

    Neuronpedia

    INDEX
    Explanations

    technical specifications related to data properties and configuration options

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

    Code, paths, and filenames

    np_acts-logits-general · gemini-2.0-flash

    optional parameter indicator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.55
    <eos>
    -0.53
     our
    -0.47
    ResumeLayout
    -0.46
    ViewFeatures
    -0.46
    autoreleasepool
    -0.45
    our
    -0.44
    LookAnd
    -0.43
    вле
    -0.42
     indeed
    -0.42
    POSITIVE LOGITS
    verwijspagina
    0.79
    มาะ
    0.76
    ">:
    0.75
    typically
    0.74
     للاسماء
    0.73
     Shakspeare
    0.73
     typically
    0.72
    hould
    0.70
    HomeAsUpEnabled
    0.70
    lihood
    0.69
    Act Density 0.282%

    No Known Activations