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

    Neuronpedia

    INDEX
    Explanations

    personal relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Filtered
    -0.07
     expectancy
    -0.06
    (am
    -0.06
    acr
    -0.06
     cao
    -0.06
    Feature
    -0.06
     Máy
    -0.06
    Continue
    -0.06
    _PATH
    -0.06
    minster
    -0.06
    POSITIVE LOGITS
    ichern
    0.07
    ivate
    0.07
     whales
    0.06
    isper
    0.06
     iCloud
    0.06
    阅读
    0.06
    ##_
    0.06
     stake
    0.06
    訂
    0.06
     Winner
    0.06
    Act Density 0.024%

    No Known Activations