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

    Neuronpedia

    INDEX
    Explanations

    code-related elements and structures, particularly those associated with function definitions and variable manipulation

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

    Code snippets with "return", "this", or "if"

    np_acts-logits-general · gemini-2.0-flash

    if and return statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RetentionPolicy
    -0.73
     chofe
    -0.72
    SBATCH
    -0.68
     Cæsar
    -0.68
     myſelf
    -0.67
     itſelf
    -0.66
     سكانية
    -0.65
    méno
    -0.65
     sanitaires
    -0.65
    astify
    -0.64
    POSITIVE LOGITS
    __);
    0.48
     _{\
    0.47
    if
    0.47
    ].(
    0.46
    _{(
    0.45
    _{
    0.44
     kunt
    0.43
     }{
    0.43
     _{
    0.43
    {
    0.42
    Act Density 0.096%

    No Known Activations