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

    Neuronpedia

    INDEX
    Explanations

    unless, except, otherwise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    to
    0.55
    ED
    0.46
    К
    0.45
    ET
    0.45
    them
    0.45
     multist
    0.44
    FL
    0.43
    Linux
    0.43
     taus
    0.40
     সম্মুখে
    0.40
    POSITIVE LOGITS
     genoeg
    0.46
    ťou
    0.45
    oc
    0.43
     Obwohl
    0.43
     Versch
    0.42
    主演
    0.41
     Joko
    0.41
    笅
    0.41
    ují
    0.41
    af
    0.40
    Act Density 0.001%

    No Known Activations