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

    Neuronpedia

    INDEX
    Explanations

    waste of time energy resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ample
    0.40
     geplant
    0.40
    给自己
    0.40
     success
    0.38
     ausreiche
    0.38
     Amount
    0.38
     comfy
    0.38
     कठिना
    0.38
     Investing
    0.37
     festivities
    0.37
    POSITIVE LOGITS
     precious
    1.25
     valuable
    1.02
     précie
    1.02
     précieux
    1.01
    貴重
    0.95
     Precious
    0.91
     Valuable
    0.80
     needlessly
    0.77
     মূল্যবান
    0.76
     değerli
    0.75
    Act Density 0.022%

    No Known Activations