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

    Neuronpedia

    INDEX
    Explanations

    Dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     occupy
    -0.07
     calcium
    -0.07
    (Resource
    -0.07
    (Screen
    -0.06
     Bik
    -0.06
     souvent
    -0.06
    neath
    -0.06
    .Subscribe
    -0.06
     bilingual
    -0.06
     flight
    -0.06
    POSITIVE LOGITS
     أول
    0.06
    анні
    0.06
    ใบ
    0.06
    لام
    0.06
    Refer
    0.06
    .Est
    0.06
    essment
    0.06
    afür
    0.06
    TZ
    0.06
    Changes
    0.06
    Act Density 0.004%

    No Known Activations