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

    Neuronpedia

    INDEX
    Explanations

    moths categorization

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pickups
    -0.07
    Language
    -0.07
    StartDate
    -0.07
    apest
    -0.06
     rooms
    -0.06
     chicken
    -0.06
     assigns
    -0.06
     Breed
    -0.06
    ليات
    -0.06
     subscribers
    -0.06
    POSITIVE LOGITS
    ereço
    0.07
    OBJ
    0.07
     "','"
    0.07
     rowspan
    0.07
     um
    0.06
    (eventName
    0.06
    ливо
    0.06
    єн
    0.06
     admir
    0.06
    हम
    0.06
    Act Density 0.002%

    No Known Activations