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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming syntax and structure

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

    Code related to file paths or names

    np_acts-logits-general · gemini-2.0-flash

    variable names and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.58
    ]}"
    -0.51
    "]);
    -0.49
     }));
    -0.49
     program
    -0.49
    стеро
    -0.48
    ]);
    -0.47
    >');
    -0.47
    ]}>
    -0.46
    ()}>
    -0.46
    POSITIVE LOGITS
    +"_
    0.90
     Efq
    0.85
     تضيفلها
    0.81
    Personensuche
    0.73
     Jefus
    0.73
    ANNES
    0.68
    +#+#
    0.68
    qrstuvwxyz
    0.67
     whoſe
    0.66
    IContainer
    0.65
    Act Density 0.189%

    No Known Activations