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

    Neuronpedia

    INDEX
    Explanations

    knowledge with intent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    తోంది
    0.49
    ండె
    0.47
    ндары
    0.43
    ähne
    0.43
    ূট
    0.41
    Politics
    0.40
     került
    0.40
    Hot
    0.40
     Kettle
    0.40
    aways
    0.39
    POSITIVE LOGITS
    س
    0.47
    พ่อ
    0.46
    سان
    0.46
    സോ
    0.45
    ศ
    0.45
    𝚘
    0.44
    の良い
    0.44
    convers
    0.43
    gallant
    0.42
    ม
    0.41
    Act Density 0.002%

    No Known Activations