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

    Neuronpedia

    INDEX
    Explanations

    道

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Seed
    -0.08
    verband
    -0.08
     Dye
    -0.08
     feather
    -0.08
    'Or
    -0.08
     Lump
    -0.08
    eded
    -0.07
     freezed
    -0.07
     dura
    -0.07
    -0.07
    POSITIVE LOGITS
     exploited
    0.11
     attackers
    0.09
    攻击
    0.09
     divul
    0.09
     explo
    0.09
    Decrypt
    0.09
     vulnerabilities
    0.09
     exploit
    0.08
     explot
    0.08
     machine
    0.08
    Act Density 0.001%
    No Known Activations