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

    Neuronpedia

    INDEX
    Explanations

    be there

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    இர
    0.44
     island
    0.43
    brew
    0.42
    island
    0.41
     shadow
    0.41
    ！】
    0.41
     crema
    0.41
     uhr
    0.41
     brooding
    0.40
    ēng
    0.40
    POSITIVE LOGITS
     कोट
    0.40
    琟
    0.36
    经历
    0.36
    Pour
    0.36
    形状
    0.35
    プレゼ
    0.34
     verwij
    0.34
    ضاء
    0.34
    налу
    0.33
     vés
    0.33
    Act Density 0.000%

    No Known Activations