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

    Neuronpedia

    INDEX
    Explanations

    flattened

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    เศร
    -0.07
    trand
    -0.07
    주택
    -0.07
     kvin
    -0.07
     Kitchen
    -0.07
    .side
    -0.06
     Yok
    -0.06
    -Allow
    -0.06
    僖
    -0.06
     amy
    -0.06
    POSITIVE LOGITS
     throughput
    0.07
     ""))↵
    0.07
    .Done
    0.07
    obe
    0.07
    Data
    0.07
    agers
    0.07
    下來
    0.07
     technique
    0.07
     mũi
    0.07
    -tone
    0.07
    Act Density 0.016%

    No Known Activations