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

    Neuronpedia

    INDEX
    Explanations

    justifying

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Revel
    -0.07
    positories
    -0.07
     abrupt
    -0.06
    967
    -0.06
     obliged
    -0.06
     Weber
    -0.06
    cq
    -0.06
    (shift
    -0.06
     Alzheimer
    -0.06
    コ
    -0.06
    POSITIVE LOGITS
     här
    0.07
     bei
    0.07
    ーティ
    0.07
     перевір
    0.06
     watering
    0.06
     इन
    0.06
     İngiliz
    0.06
    �
    0.06
    قق
    0.06
     {}
↵
    0.06
    Act Density 0.072%

    No Known Activations