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

    Neuronpedia

    INDEX
    Explanations

    say 200

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Domains
    -0.08
     urlString
    -0.07
    tau
    -0.07
    EMENT
    -0.07
    eta
    -0.06
    包
    -0.06
    ミュ
    -0.06
    debug
    -0.06
    隐
    -0.06
     ldb
    -0.06
    POSITIVE LOGITS
    "is
    0.06
    ّة
    0.06
    -ли
    0.06
     Basis
    0.06
     woven
    0.06
    athom
    0.06
     оброб
    0.06
     midst
    0.06
    Hi
    0.06
     الحديث
    0.06
    Act Density 0.005%

    No Known Activations