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

    Neuronpedia

    INDEX
    Explanations

    . this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nějak
    0.59
     publicités
    0.56
    dyž
    0.56
     خیلی
    0.55
     então
    0.55
     però
    0.54
     morf
    0.54
    Rồi
    0.53
     sommige
    0.52
     regex
    0.52
    POSITIVE LOGITS
    This
    0.59
     This
    0.59
     Included
    0.55
     Director
    0.55
    provides
    0.54
    这将
    0.53
     Professor
    0.53
     Designed
    0.51
     Powered
    0.51
     මෙම
    0.50
    Act Density 0.023%

    No Known Activations