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

    Neuronpedia

    INDEX
    Explanations

    causes and relations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    0.50
    を
    0.47
     ถึง
    0.45
    カーテン
    0.44
     را
    0.43
     נו
    0.43
     و
    0.43
    majority
    0.43
    して
    0.42
     ו
    0.42
    POSITIVE LOGITS
     proposing
    0.41
    RelativeTo
    0.41
     impressão
    0.41
    ابقات
    0.41
     Veteran
    0.41
    తర
    0.41
     Platinum
    0.40
    न्ही
    0.39
    ajos
    0.39
    ટક
    0.39
    Act Density 0.068%

    No Known Activations