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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kle
    -0.07
     Action
    -0.07
     Effects
    -0.07
     Василь
    -0.06
    ovaný
    -0.06
    _buckets
    -0.06
    getResponse
    -0.06
    _predictions
    -0.06
    .Gson
    -0.06
    Bucket
    -0.06
    POSITIVE LOGITS
    \Carbon
    0.07
     punitive
    0.06
     спад
    0.06
    pal
    0.06
    �
    0.06
    clusions
    0.06
    _detector
    0.06
    licensed
    0.06
     квар
    0.06
     disappears
    0.06
    Act Density 0.018%

    No Known Activations