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

    Neuronpedia

    INDEX
    Explanations

    estimator

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CCT
    -0.08
    امعة
    -0.07
     Med
    -0.07
     Dame
    -0.07
    nect
    -0.07
     sẵn
    -0.07
     sint
    -0.06
    רת
    -0.06
    rgyz
    -0.06
     PubMed
    -0.06
    POSITIVE LOGITS
    job
    0.07
     prizes
    0.07
    .Accessible
    0.07
    .finished
    0.07
    社会实践
    0.06
     sold
    0.06
    tooltip
    0.06
    \Collection
    0.06
     CSV
    0.06
    .Rectangle
    0.06
    Act Density 0.001%

    No Known Activations