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

    Neuronpedia

    INDEX
    Explanations

    specific programming test cases or related components in code

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

    java tests and math libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     brancas
    -0.34
     zákon
    -0.32
    movq
    -0.31
     amarillas
    -0.31
     déclarations
    -0.30
     rarement
    -0.30
    цездатний
    -0.30
    SharedCtor
    -0.30
     blancas
    -0.30
     dejes
    -0.29
    POSITIVE LOGITS
    tagHelperRunner
    0.60
     experiments
    0.58
     experiment
    0.56
     terrarium
    0.56
     crossorigin
    0.55
     demonstrations
    0.54
     betweenstory
    0.54
     experim
    0.54
     bunnies
    0.53
     demos
    0.53
    Act Density 0.003%

    No Known Activations