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

    Neuronpedia

    INDEX
    Explanations

    because of possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ہ
    1.02
    ين
    1.00
    أ
    0.94
    fact
    0.93
    thousand
    0.90
    er
    0.85
    এর
    0.84
    ທ່ານ
    0.83
    প্র
    0.83
     прошла
    0.83
    POSITIVE LOGITS
     course
    1.45
     sorts
    1.37
     how
    1.25
     COURSE
    1.23
     intermediaries
    1.16
     layoffs
    1.14
     what
    1.14
     inherent
    1.12
     avenues
    1.12
     catalysis
    1.11
    Act Density 0.003%

    No Known Activations