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

    Neuronpedia

    INDEX
    Explanations

    essential, crucial, standard, optional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prioritizing
    0.48
    貴重
    0.47
     priority
    0.42
     Priority
    0.42
     valuing
    0.41
     인기
    0.40
     benefitting
    0.40
     valued
    0.40
     Sought
    0.39
    덥
    0.39
    POSITIVE LOGITS
    标准
    0.48
     corrected
    0.48
     optional
    0.48
     standard
    0.45
    Standard
    0.45
     idi
    0.45
    optional
    0.44
     അന്ത
    0.44
     নতুন
    0.44
    Optional
    0.43
    Act Density 0.031%

    No Known Activations