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

    Neuronpedia

    INDEX
    Explanations

    terms related to self-reference and self-management

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

    "self"

    np_acts-logits-general · gemini-2.0-flash

    self words and self identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.86
    DockStyle
    -0.64
     الحره
    -0.62
    __*/
    -0.57
    ConverterFactory
    -0.56
     nakalista
    -0.56
     BitmapFactory
    -0.56
    ::*;
    -0.54
    StoryboardSegue
    -0.53
     orthodoxy
    -0.52
    POSITIVE LOGITS
     Self
    1.24
     self
    1.21
     SELF
    1.14
    Self
    1.10
    SELF
    0.99
    self
    0.83
    Selbst
    0.78
     Selbst
    0.74
     Само
    0.66
    Само
    0.60
    Act Density 0.093%

    No Known Activations