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

    Neuronpedia

    INDEX
    Explanations

    Toxicity/health problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    675
    -0.07
    ws
    -0.06
    ेव
    -0.06
     이는
    -0.06
    .testng
    -0.06
    ancer
    -0.06
    268
    -0.06
    ویس
    -0.06
    _comp
    -0.06
    iations
    -0.06
    POSITIVE LOGITS
    erie
    0.07
     East
    0.06
     Can
    0.06
    .Cryptography
    0.06
     sulph
    0.06
     terre
    0.06
     EDIT
    0.06
     आत
    0.06
    _net
    0.06
    adamente
    0.06
    Act Density 0.041%

    No Known Activations