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

    Neuronpedia

    INDEX
    Explanations

    head

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    济
    -0.07
    Chain
    -0.07
    ного
    -0.06
    ks
    -0.06
    Median
    -0.06
     sene
    -0.06
    rai
    -0.06
     Bitmap
    -0.06
     Various
    -0.06
    buf
    -0.06
    POSITIVE LOGITS
    779
    0.07
     hukuk
    0.07
     xmlhttp
    0.06
     hasNext
    0.06
    CONFIG
    0.06
     UserProfile
    0.06
    (square
    0.06
     vole
    0.06
     huz
    0.06
    Reducers
    0.06
    Act Density 0.004%

    No Known Activations