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

    Neuronpedia

    INDEX
    Explanations

    possessive followed by noun attribute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Things
    0.73
     結果
    0.66
    Scenario
    0.64
    Company
    0.63
    Similarly
    0.61
    Result
    0.60
    事項
    0.60
     Amounts
    0.60
    Companies
    0.59
    Amount
    0.59
    POSITIVE LOGITS
     own
    1.52
     ability
    1.01
     abilities
    0.89
     inhabitants
    0.89
     próprias
    0.86
     shortcomings
    0.85
     respective
    0.84
     propias
    0.83
     propres
    0.82
    own
    0.81
    Act Density 0.646%

    No Known Activations