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

    Neuronpedia

    INDEX
    Explanations

    rules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Funeral
    -0.07
    \F
    -0.07
    Transformation
    -0.06
    rack
    -0.06
    .lb
    -0.06
     fourth
    -0.06
    .checkSelfPermission
    -0.06
     CI
    -0.06
     lst
    -0.06
    Cr
    -0.06
    POSITIVE LOGITS
     pelvic
    0.07
     التو
    0.07
     types
    0.07
     tog
    0.07
    ีย
    0.06
     gösterir
    0.06
    养
    0.06
    active
    0.06
     بودند
    0.06
     elit
    0.06
    Act Density 0.025%

    No Known Activations