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

    Neuronpedia

    INDEX
    Explanations

    references to internal structures and systems in various contexts

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

    "internal"

    np_acts-logits-general · gemini-2.0-flash

    internal followed by system components or processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.75
    [])
    -0.70
     McClure
    -0.67
    "]);
    -0.65
     sentito
    -0.65
    [];
    -0.65
     Kruse
    -0.65
     };
    -0.64
    zyści
    -0.63
    "},
    -0.63
    POSITIVE LOGITS
     INTERNAL
    0.80
    ternal
    0.80
     internal
    0.77
     Internal
    0.76
    Internal
    0.70
    INTERNAL
    0.68
    internal
    0.65
     internally
    0.64
    EXTERNAL
    0.60
     Intern
    0.58
    Act Density 0.190%

    No Known Activations