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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Windsor
    -0.07
    typed
    -0.07
     `.
    -0.07
    標準
    -0.06
    `.
    -0.06
    _expiry
    -0.06
    ').
    -0.06
    desired
    -0.06
     Try
    -0.06
     注意
    -0.06
    POSITIVE LOGITS
    IntArray
    0.07
    .Automation
    0.06
    .beh
    0.06
    Parms
    0.06
     dps
    0.06
    être
    0.06
    Mismatch
    0.06
    pdb
    0.06
    εια
    0.06
    YPRE
    0.06
    Act Density 0.215%

    No Known Activations