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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .trim
    -0.07
     indir
    -0.06
     MATRIX
    -0.06
     만들
    -0.06
    _article
    -0.06
    _et
    -0.06
     lives
    -0.06
    flate
    -0.06
     manifest
    -0.06
     škol
    -0.06
    POSITIVE LOGITS
    Anthony
    0.07
    Classification
    0.07
     bedding
    0.07
     Anthony
    0.07
    -volume
    0.06
    竞
    0.06
     Epic
    0.06
     Elizabeth
    0.06
    Henry
    0.06
     Battalion
    0.06
    Act Density 0.002%

    No Known Activations