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

    Neuronpedia

    INDEX
    Explanations

    Engineering Physics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    哠
    0.50
    Consumers
    0.47
    Female
    0.46
    Fisher
    0.46
    Jesse
    0.44
    Cyclone
    0.44
    骷
    0.43
    ᑲ
    0.43
    Fs
    0.43
    кте
    0.43
    POSITIVE LOGITS
     prohibits
    0.51
     子
    0.46
     Says
    0.44
     promotes
    0.44
     ix
    0.44
     prevents
    0.44
     explains
    0.43
     requires
    0.43
    рной
    0.43
     complicates
    0.43
    Act Density 0.004%

    No Known Activations