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

    Neuronpedia

    INDEX
    Explanations

    protect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ItemAt
    -0.06
    omu
    -0.06
    utan
    -0.06
    _Public
    -0.06
     Shutterstock
    -0.06
    平方公里
    -0.06
     senha
    -0.06
     disruptions
    -0.06
    ολ
    -0.06
    ╝
    -0.06
    POSITIVE LOGITS
     WEIGHT
    0.06
    ствен
    0.06
    атегор
    0.06
     çı
    0.06
     색
    0.06
    他們
    0.06
     grate
    0.06
     вар
    0.06
     Edwards
    0.06
     Ast
    0.06
    Act Density 0.004%

    No Known Activations