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

    Neuronpedia

    INDEX
    Explanations

    what to do explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rix
    0.48
    முக
    0.46
    stanford
    0.44
    roly
    0.43
    pyrim
    0.43
    preprocess
    0.42
    inim
    0.42
    ăn
    0.41
    idade
    0.41
    ely
    0.40
    POSITIVE LOGITS
     productions
    0.51
     nowoczes
    0.49
     MAGAZINE
    0.48
     WORD
    0.47
     Magazine
    0.45
    他们
    0.44
     कलाकारों
    0.44
     ROY
    0.44
    本の
    0.44
     magazines
    0.44
    Act Density 0.009%

    No Known Activations