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

    Neuronpedia

    INDEX
    Explanations

    german and swedish languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bekommen
    0.46
     krijgen
    0.46
     получите
    0.44
     পাওয়া
    0.43
     становятся
    0.42
     får
    0.42
     komme
    0.42
     получила
    0.41
     encontrar
    0.41
     kommen
    0.41
    POSITIVE LOGITS
     epoch
    0.44
     employs
    0.43
     Hood
    0.39
     Sob
    0.39
     employ
    0.39
     adjust
    0.39
     fein
    0.38
     مثلا
    0.37
     mashed
    0.37
     Søren
    0.37
    Act Density 0.001%

    No Known Activations