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

    Neuronpedia

    INDEX
    Explanations

    occurrences of environment variable references in code

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

    parameters and arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quickly
    -0.32
     FontWeight
    -0.32
     Mensch
    -0.29
     Che
    -0.26
     Schnell
    -0.26
     gone
    -0.26
     and
    -0.26
     of
    -0.26
     offers
    -0.26
    イ
    -0.26
    POSITIVE LOGITS
     params
    1.38
    params
    1.12
     Params
    0.93
    Params
    0.92
     Parameters
    0.82
     useParams
    0.81
    PARAMS
    0.81
    AddTagHelper
    0.81
     kasarigan
    0.76
     parameters
    0.76
    Act Density 0.001%

    No Known Activations