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

    Neuronpedia

    INDEX
    Explanations

    lip and gender

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     réalisée
    0.39
     WIDTH
    0.39
    WIDTH
    0.38
     luckily
    0.37
    幅
    0.37
    ído
    0.35
    䬲
    0.35
     platter
    0.35
    Width
    0.34
     čini
    0.34
    POSITIVE LOGITS
    لاه
    0.38
     米
    0.38
     shortened
    0.37
    rd
    0.37
     ได้
    0.37
    低い
    0.37
    रह
    0.36
    atius
    0.36
     Champagne
    0.36
     likewise
    0.35
    Act Density 0.000%

    No Known Activations