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

    Neuronpedia

    INDEX
    Explanations

    class/subtype

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Gas
    -0.08
     Gas
    -0.07
     Lyon
    -0.06
    nist
    -0.06
     rivalry
    -0.06
    联系
    -0.06
     qui
    -0.06
    "All
    -0.06
    اصل
    -0.06
    lendirme
    -0.06
    POSITIVE LOGITS
    tej
    0.07
     Lei
    0.07
    APSHOT
    0.06
    worth
    0.06
    -prof
    0.06
     resultant
    0.06
    !,
    0.06
    .Aggressive
    0.06
    etes
    0.06
    ת
    0.06
    Act Density 0.004%

    No Known Activations