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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns describe their attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     another
    0.17
     bestaat
    0.17
    ।
    0.16
    ↵
    0.16
     becomes
    0.16
                             
    0.15
     they
    0.15
     belongs
    0.15
     ん
    0.15
     būti
    0.15
    POSITIVE LOGITS
     approach
    0.23
     unique
    0.23
     methodology
    0.22
     overarching
    0.22
    独特的
    0.21
     overall
    0.21
     enigmatic
    0.21
     penchant
    0.20
     storytelling
    0.20
     particular
    0.20
    Act Density 0.223%

    No Known Activations