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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kim
    -0.07
     wikipedia
    -0.07
     recall
    -0.07
     neglig
    -0.07
    ΡΙ
    -0.07
     Friday
    -0.07
    .Struct
    -0.06
    ailand
    -0.06
    IV
    -0.06
     natur
    -0.06
    POSITIVE LOGITS
    .Dot
    0.06
    \\"
    0.06
     coorden
    0.06
     ammon
    0.06
    ้งาน
    0.05
     thư
    0.05
    PlainOldData
    0.05
     الحل
    0.05
     Siber
    0.05
     USED
    0.05
    Act Density 0.025%

    No Known Activations