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

    Neuronpedia

    INDEX
    Explanations

    better days or decades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vetting
    0.55
     homeschooling
    0.53
     salary
    0.50
     windscreen
    0.49
     recommended
    0.47
     striving
    0.47
     vetted
    0.46
     salaries
    0.45
     homemade
    0.45
     enhancing
    0.45
    POSITIVE LOGITS
    т
    0.50
    н
    0.48
    ты
    0.46
    arci
    0.45
    ANIUM
    0.44
    у
    0.43
    ANIEL
    0.43
    ɠ
    0.43
    ྟ
    0.42
    Ver
    0.42
    Act Density 0.008%

    No Known Activations