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

    Neuronpedia

    INDEX
    Explanations

    hundreds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <>(
    -0.08
     conspicuous
    -0.07
    ACTIVE
    -0.07
     حيث
    -0.06
     สำหร
    -0.06
    ξει
    -0.06
     consect
    -0.06
     thereby
    -0.06
    ственное
    -0.06
    strukce
    -0.06
    POSITIVE LOGITS
    美
    0.07
    奈
    0.06
    езпеч
    0.06
     cousins
    0.06
    пе
    0.06
     वन
    0.06
     Reasons
    0.06
     homemade
    0.06
    γγ
    0.06
    '},
↵
    0.06
    Act Density 0.003%

    No Known Activations