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

    Neuronpedia

    INDEX
    Explanations

    LoRA

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initio
    0.45
     рубе
    0.44
     पॉलिटी
    0.43
     χρόνο
    0.39
    ligence
    0.38
     ishlab
    0.38
     ï
    0.38
     fogo
    0.38
    oulis
    0.37
     aște
    0.37
    POSITIVE LOGITS
    📍
    0.46
    蛀
    0.44
     Tajik
    0.43
    Cart
    0.42
    Sugar
    0.42
    🥲
    0.41
     Señ
    0.41
    🫠
    0.41
    場所
    0.41
    Attachment
    0.40
    Act Density 0.038%

    No Known Activations