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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +w
    -0.07
     biến
    -0.07
    их
    -0.06
    σκευή
    -0.06
     가장
    -0.06
    _usage
    -0.06
    findOne
    -0.06
     HOUR
    -0.06
    Air
    -0.06
    模型
    -0.06
    POSITIVE LOGITS
    ucceeded
    0.06
     Lennon
    0.06
    (filePath
    0.06
    /en
    0.06
    .setContentType
    0.06
    律
    0.06
    pic
    0.06
     porn
    0.06
    izzling
    0.06
     Norse
    0.06
    Act Density 0.005%

    No Known Activations