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

    Neuronpedia

    INDEX
    Explanations

    starting requests with 'I'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mid
    0.38
     comfort
    0.38
     decorative
    0.37
     obscure
    0.37
     sensitive
    0.36
     anxious
    0.36
     noisy
    0.36
     gear
    0.36
     childcare
    0.36
     Musica
    0.36
    POSITIVE LOGITS
    เริ่ม
    0.45
     시작
    0.44
     başlayalım
    0.44
     beginnt
    0.44
     প্রথমেই
    0.44
     beginnen
    0.43
     начну
    0.43
    you
    0.42
     শুরু
    0.42
     начинают
    0.42
    Act Density 0.032%

    No Known Activations