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

    Neuronpedia

    INDEX
    Explanations

    double meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     single
    0.49
     precisely
    0.44
    闲
    0.42
     design
    0.40
     provider
    0.40
    单
    0.40
     Privilege
    0.39
     Taken
    0.39
     Obviously
    0.38
     clearing
    0.38
    POSITIVE LOGITS
     стандарта
    0.44
     meanings
    0.43
    Standards
    0.43
     entendre
    0.42
     syllables
    0.42
    勤務
    0.40
    standards
    0.40
    惊喜
    0.40
     entend
    0.40
     bilayers
    0.40
    Act Density 0.008%

    No Known Activations