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

    Neuronpedia

    INDEX
    Explanations

    categorized, with details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    op
    0.49
    orbital
    0.49
    osp
    0.47
    five
    0.47
    ok
    0.46
    ocl
    0.46
    ined
    0.46
    ard
    0.45
    seven
    0.44
    ibr
    0.44
    POSITIVE LOGITS
     для
    0.71
     في
    0.70
    ใน
    0.69
     dengan
    0.66
     với
    0.62
     على
    0.62
     pentru
    0.61
     برای
    0.61
     untuk
    0.61
     with
    0.59
    Act Density 0.022%

    No Known Activations