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

    Neuronpedia

    INDEX
    Explanations

    code loop initiations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पोषक
    0.41
     வள்ளி
    0.40
    🚺
    0.40
    😩
    0.39
     algodón
    0.38
    구요
    0.38
    😂😂
    0.37
     Pflanzen
    0.37
     пье
    0.37
    💆
    0.37
    POSITIVE LOGITS
     it
    0.46
    ↵
    0.44
     they
    0.43
     their
    0.42
     items
    0.42
     item
    0.42
    if
    0.41
     attributes
    0.40
     speaker
    0.40
    उनकी
    0.40
    Act Density 0.182%

    No Known Activations