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

    Neuronpedia

    INDEX
    Explanations

    Java method definitions and return statements in the code

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

    "this" or "self" in code

    np_acts-logits-general · gemini-2.0-flash

    `this`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.46
    NameInMap
    -0.45
    MigrationBuilder
    -0.43
    kning
    -0.42
    RegistryLite
    -0.41
     محفوظة
    -0.41
    devise
    -0.41
    вної
    -0.40
    culously
    -0.40
    LookAnd
    -0.39
    POSITIVE LOGITS
     this
    1.18
    this
    1.11
    self
    0.96
     myself
    0.95
     THIS
    0.94
    Myself
    0.92
     oneself
    0.90
     selves
    0.89
    selves
    0.89
     me
    0.88
    Act Density 0.132%

    No Known Activations