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

    Neuronpedia

    INDEX
    Explanations

    words forming descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    하는데
    0.47
    uak
    0.46
    endim
    0.46
    ave
    0.46
    ikal
    0.46
    out
    0.44
    브
    0.44
     전에
    0.43
    iya
    0.43
    upon
    0.43
    POSITIVE LOGITS
     excursions
    0.54
    ر
    0.49
     hurling
    0.48
     painful
    0.48
     Throat
    0.46
    赵
    0.46
    Mara
    0.46
     unseren
    0.45
    р
    0.45
     Mara
    0.44
    Act Density 0.001%

    No Known Activations