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

    Neuronpedia

    INDEX
    Explanations

    language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Æ
    -0.07
    нюю
    -0.07
     PLATFORM
    -0.07
     设
    -0.06
    igroup
    -0.06
     ice
    -0.06
    _REQUIRE
    -0.06
    iest
    -0.06
    ество
    -0.06
    Pale
    -0.06
    POSITIVE LOGITS
     hourly
    0.08
     behaves
    0.07
     INCIDENT
    0.07
     flavour
    0.07
    oug
    0.06
    (@(
    0.06
     heritage
    0.06
     nhà
    0.06
    _VOICE
    0.06
    .formData
    0.06
    Act Density 0.002%

    No Known Activations