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

    Neuronpedia

    INDEX
    Explanations

    safety guidelines opener

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    基本的に
    0.42
    Emily
    0.41
    kir
    0.40
     Emily
    0.40
    chil
    0.38
    Flicky
    0.38
    diphenyl
    0.37
     kilogram
    0.37
    adeep
    0.37
    Sud
    0.36
    POSITIVE LOGITS
     symbi
    0.39
     synerg
    0.37
     Martin
    0.37
     safer
    0.36
    રે
    0.35
     stress
    0.35
     MARTIN
    0.34
    びに
    0.34
     Re
    0.34
     rebut
    0.34
    Act Density 0.008%

    No Known Activations