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

    Neuronpedia

    INDEX
    Explanations

    conclusion indicators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     лист
    -0.07
    щего
    -0.07
     cụ
    -0.06
     �
    -0.06
    тик
    -0.06
    婆
    -0.06
     Paragraph
    -0.06
     bew
    -0.06
    �
    -0.06
     headphone
    -0.06
    POSITIVE LOGITS
     तक
    0.07
    iles
    0.07
     for
    0.07
    .times
    0.07
    .Flags
    0.06
    cluding
    0.06
     Traditional
    0.06
    o
    0.06
     nodeId
    0.06
    .every
    0.06
    Act Density 0.052%

    No Known Activations