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

    Neuronpedia

    INDEX
    Explanations

    function definitions and related assertions in code

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

    should recognize or return

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ControllerBase
    -0.42
    jsii
    -0.41
    ynomial
    -0.38
     ComVisible
    -0.37
    hamster
    -0.36
    rophoresis
    -0.36
    Insee
    -0.35
     necesariamente
    -0.35
     iprot
    -0.35
     desmotivaciones
    -0.35
    POSITIVE LOGITS
    0.58
    IVEREF
    0.52
     mix
    0.47
     mis
    0.47
    verwijspagina
    0.47
     sal
    0.45
    ########.
    0.45
     courting
    0.44
     mixes
    0.44
    ngdoc
    0.44
    Act Density 0.016%

    No Known Activations