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

    Neuronpedia

    INDEX
    Explanations

    PhD qualifications or retired professions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.50
     ambitious
    0.49
    ismo
    0.45
    ige
    0.45
     nationality
    0.45
    Sim
    0.42
     favored
    0.41
    很好的
    0.41
    Workspace
    0.40
    Table
    0.40
    POSITIVE LOGITS
     और
    0.60
     και
    0.57
     и
    0.57
     এবং
    0.55
     आणि
    0.54
     Uygh
    0.53
    และ
    0.52
     và
    0.51
     ἀ
    0.51
    ແລະ
    0.50
    Act Density 0.001%

    No Known Activations