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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yandan
    -0.07
    Anti
    -0.07
    .replaceAll
    -0.07
    ocrisy
    -0.07
    决
    -0.07
    Anth
    -0.07
    行业
    -0.06
    rush
    -0.06
     film
    -0.06
    Meanwhile
    -0.06
    POSITIVE LOGITS
    .Map
    0.07
    чит
    0.07
    २०
    0.06
     dialogue
    0.06
    θυν
    0.06
    afka
    0.06
     Lights
    0.06
    xCE
    0.06
     Req
    0.06
    _light
    0.06
    Act Density 0.013%

    No Known Activations