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

    Neuronpedia

    INDEX
    Explanations

    technical terms and programming-related concepts

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

    Java-related code or documentation examples

    np_acts-logits-general · gemini-2.0-flash

    Java classes and instances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FunctionFlags
    -0.52
     FUNC
    -0.49
    FUNC
    -0.49
     Funktion
    -0.49
    function
    -0.48
     function
    -0.47
    lood
    -0.46
     lenker
    -0.45
     mitochondrial
    -0.45
     functions
    -0.44
    POSITIVE LOGITS
     java
    1.09
     Java
    1.08
    java
    0.99
     bean
    0.96
    Java
    0.95
     beans
    0.87
    JDK
    0.84
     JDK
    0.84
     {@
    0.84
    bean
    0.83
    Act Density 0.689%

    No Known Activations