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

    Neuronpedia

    INDEX
    Explanations

    order or chronological sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     laryng
    0.94
     suppos
    0.92
     outcrops
    0.83
    們
    0.82
    温泉
    0.82
     superpowers
    0.80
    ू
    0.79
     dapp
    0.79
     schematically
    0.79
     homomorphism
    0.79
    POSITIVE LOGITS
     убы
    0.71
     بندی
    0.71
    िक
    0.69
    क्रम
    0.66
    ar
    0.65
    ᑭ
    0.65
     ngũ
    0.65
    Hilo
    0.63
    ுங்கள்
    0.61
    িক
    0.61
    Act Density 0.182%

    No Known Activations