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

    Neuronpedia

    INDEX
    Explanations

    installing packages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oed
    0.41
    मित्र
    0.38
    IVER
    0.36
    amb
    0.36
    reduced
    0.35
    UEN
    0.35
     உருவாக்கி
    0.35
    wig
    0.35
    endar
    0.34
    wit
    0.34
    POSITIVE LOGITS
     подобных
    0.73
     religions
    0.61
    こういう
    0.60
     இதுபோன்ற
    0.59
     জিনিসের
    0.57
     подобные
    0.57
     currencies
    0.56
     ANY
    0.55
     qualsiasi
    0.55
     monopolies
    0.54
    Act Density 0.048%

    No Known Activations