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

    Neuronpedia

    INDEX
    Explanations

    self

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nay
    -0.07
    ologia
    -0.06
    dfa
    -0.06
     фай
    -0.06
     खर
    -0.06
     Amber
    -0.06
    :↵↵↵↵
    -0.06
     응
    -0.06
    .RowCount
    -0.06
     наче
    -0.06
    POSITIVE LOGITS
    .Math
    0.07
    �
    0.07
    <Props
    0.06
     управління
    0.06
    firebase
    0.06
    専
    0.06
     Thr
    0.06
    midd
    0.06
    นก
    0.06
     �
    0.06
    Act Density 0.002%

    No Known Activations