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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating leadership or command structures in organizations

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

    led by entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    béco
    -0.48
    Lugares
    -0.48
    MigrationBuilder
    -0.44
     instin
    -0.42
     Offisielt
    -0.40
    contentLoaded
    -0.39
    čník
    -0.39
    言
    -0.38
    rativa
    -0.36
     Pemain
    -0.35
    POSITIVE LOGITS
    AxisAlignment
    0.54
     <=",
    0.53
    ArgsConstructor
    0.52
    withId
    0.48
     defaultstate
    0.47
     headed
    0.46
     chaired
    0.46
    を中心に
    0.46
    を中心
    0.46
     veden
    0.45
    Act Density 0.046%

    No Known Activations