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

    Neuronpedia

    INDEX
    Explanations

    ethical tension

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    že
    0.31
    s
    0.30
    細菌
    0.29
    ﺔ
    0.29
    nsan
    0.29
     kanssa
    0.29
    你
    0.28
    enuine
    0.27
    нії
    0.27
    س
    0.27
    POSITIVE LOGITS
     embold
    0.35
    지
    0.32
    G
    0.30
     differentiator
    0.28
     misappropri
    0.28
    지와
    0.28
    გუ
    0.27
    and
    0.27
     intent
    0.27
    ర్
    0.26
    Act Density 0.000%

    No Known Activations