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

    Neuronpedia

    INDEX
    Explanations

    gifts and dedications to others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     or
    -0.95
    西亚
    -0.85
     categorized
    -0.85
     charged
    -0.84
     современных
    -0.82
     encountered
    -0.81
     paus
    -0.80
     labeled
    -0.80
     farther
    -0.79
     generated
    -0.78
    POSITIVE LOGITS
     deserves
    1.16
     služ
    0.98
     deserving
    0.98
     birthday
    0.98
    during
    0.92
     Länge
    0.89
     ausein
    0.88
     deserve
    0.88
    nieren
    0.86
    ="?
    0.86
    Act Density 0.033%

    No Known Activations