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

    Neuronpedia

    INDEX
    Explanations

    cities and regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     useContext
    0.43
    πι
    0.39
     FP
    0.37
    toBe
    0.36
    盼
    0.36
    ânico
    0.36
    悽
    0.36
     rose
    0.35
     роз
    0.35
     Sequelize
    0.35
    POSITIVE LOGITS
     Ark
    0.53
    Ark
    0.51
     Wyoming
    0.46
    kom
    0.44
     Kipp
    0.43
     kredit
    0.42
     kettle
    0.41
     meravigli
    0.41
    credit
    0.40
    Kom
    0.40
    Act Density 0.001%

    No Known Activations