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

    Neuronpedia

    INDEX
    Explanations

    't' following quote

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.59
    dır
    0.57
    i
    0.54
    g
    0.54
    dz
    0.53
    dodge
    0.53
    daki
    0.52
    doesn
    0.52
    dod
    0.51
    What
    0.50
    POSITIVE LOGITS
     এছাড়াও
    0.50
     Sabemos
    0.46
     규모
    0.46
    hör
    0.46
    に関しては
    0.45
     производстве
    0.44
     Lebensmittel
    0.44
    机遇
    0.44
     முக்கியமான
    0.44
    airo
    0.43
    Act Density 0.003%

    No Known Activations