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

    Neuronpedia

    INDEX
    Explanations

    line thickness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     {};
    0.45
    {};
    0.42
     peces
    0.42
     गोष्ट
    0.41
    PAR
    0.38
     தண்ண
    0.38
     घेतला
    0.38
    kania
    0.38
    egraphics
    0.37
     प्रश्‍
    0.37
    POSITIVE LOGITS
     thick
    0.57
    thick
    0.47
     Thick
    0.44
    ultra
    0.38
     ultra
    0.37
     épais
    0.37
    retrieve
    0.36
     densely
    0.36
    厚
    0.36
     pro
    0.35
    Act Density 0.002%

    No Known Activations