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

    Neuronpedia

    INDEX
    Explanations

    possessive relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     that
    0.51
     it
    0.50
     you
    0.48
     a
    0.47
     the
    0.47
    에
    0.47
     this
    0.47
     -
    0.46
     =
    0.44
     there
    0.44
    POSITIVE LOGITS
     own
    0.48
     வகையான
    0.45
    自身の
    0.44
     ability
    0.43
     predicament
    0.43
    自己的
    0.42
     abilities
    0.42
     multifaceted
    0.42
     capabilities
    0.41
     propres
    0.41
    Act Density 0.056%

    No Known Activations