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

    Neuronpedia

    INDEX
    Explanations

    anonymous

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ffect
    -0.06
     Kylie
    -0.06
     kings
    -0.06
     Colour
    -0.06
     colour
    -0.06
    .Blue
    -0.05
     Dahl
    -0.05
    sell
    -0.05
    üstü
    -0.05
    ्ल
    -0.05
    POSITIVE LOGITS
     anonymously
    0.08
     anonymous
    0.08
     anonymity
    0.08
     Anonymous
    0.08
    anonymous
    0.08
     anon
    0.07
    aný
    0.07
     popis
    0.07
            ↵↵
    0.07
    //---------------------------------------------------------------------------↵↵
    0.07
    Act Density 0.005%

    No Known Activations