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

    Neuronpedia

    INDEX
    Explanations

    exploitation significant age power imbalance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _{*}(
    0.41
    aisesti
    0.40
    irable
    0.39
    ᓕ
    0.37
    еру
    0.37
     وعرف
    0.37
    Officers
    0.36
    Ordinary
    0.36
    émy
    0.35
    物资
    0.35
    POSITIVE LOGITS
     Fitness
    0.41
     Tablet
    0.41
     আতঙ্ক
    0.40
     CC
    0.39
     કો
    0.39
     Fel
    0.38
    HH
    0.38
     JJ
    0.38
     CCS
    0.38
     rep
    0.37
    Act Density 0.000%

    No Known Activations