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

    Neuronpedia

    INDEX
    Explanations

    independent of other factors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    邗
    0.44
     বারবার
    0.40
     बखूबी
    0.39
     allong
    0.39
     pox
    0.37
     OSI
    0.36
    暂
    0.35
     hop
    0.35
     сих
    0.35
    TISE
    0.35
    POSITIVE LOGITS
     intrinsic
    0.80
    intrinsic
    0.80
     unabhängig
    0.77
    Intrinsic
    0.70
     незале
    0.70
     independently
    0.69
     preexisting
    0.68
     intrinsically
    0.68
     independent
    0.67
     autonomously
    0.66
    Act Density 0.089%

    No Known Activations