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

    Neuronpedia

    INDEX
    Explanations

    arrest, SQL, ice, web

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Compiler
    0.48
    factorial
    0.48
    Pain
    0.46
     Katalog
    0.46
    Reduction
    0.45
     reali
    0.45
    Problem
    0.44
     Zika
    0.43
     timescales
    0.43
    บริหาร
    0.43
    POSITIVE LOGITS
     específ
    0.54
     olev
    0.49
     neither
    0.44
     briefly
    0.40
    洄
    0.40
     Accessed
    0.39
     caregiver
    0.39
     केवळ
    0.39
    c
    0.39
    ユーザー
    0.38
    Act Density 0.010%

    No Known Activations