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

    Neuronpedia

    INDEX
    Explanations

    more, begins, age

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    риа
    0.37
     kama
    0.36
    Disagree
    0.35
     winter
    0.34
    ياء
    0.34
    料理
    0.33
     WINTER
    0.33
     endors
    0.33
     зимой
    0.33
    舞
    0.33
    POSITIVE LOGITS
    ︎
    0.36
     et
    0.34
     ή
    0.34
    嚧
    0.34
     rohkem
    0.34
    这将
    0.33
    มากขึ้น
    0.33
     /=
    0.32
     ശക്തി
    0.32
     കൂടുതല്‍
    0.32
    Act Density 0.001%

    No Known Activations