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

    Neuronpedia

    INDEX
    Explanations

    professions and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     confusing
    0.28
     douloureuse
    0.28
    死亡
    0.28
     variability
    0.27
     কমিটি
    0.27
     plaatsen
    0.27
    場合があります
    0.27
     clumps
    0.26
     digestible
    0.26
     drowsiness
    0.26
    POSITIVE LOGITS
     musician
    0.53
     strategist
    0.51
     researcher
    0.50
     educator
    0.50
     theorist
    0.49
     raconte
    0.49
     entrepreneur
    0.49
     craftsman
    0.48
     conno
    0.48
     campaigner
    0.47
    Act Density 0.099%

    No Known Activations