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

    Neuronpedia

    INDEX
    Explanations

    unfair features or changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    茶叶
    0.38
    電源
    0.37
    ijden
    0.36
     setempat
    0.36
    孑
    0.36
     startled
    0.35
     ovip
    0.34
    电源
    0.34
    关节
    0.34
    各自
    0.34
    POSITIVE LOGITS
     botched
    0.55
     unfairly
    0.54
     unfair
    0.50
     fanbase
    0.48
     mandated
    0.45
     revamped
    0.44
     needlessly
    0.44
     outrage
    0.44
     layoffs
    0.44
     hype
    0.43
    Act Density 0.137%

    No Known Activations