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

    Neuronpedia

    INDEX
    Explanations

    fear and worry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Сле
    0.39
    ັນ
    0.38
    traj
    0.38
     ध्यान
    0.37
    趣
    0.37
    seag
    0.37
     அலு
    0.37
    interested
    0.37
     ಗಮನ
    0.36
     Κα
    0.35
    POSITIVE LOGITS
     fear
    1.04
     fears
    1.03
     uncertainty
    1.01
     miedo
    1.00
     insecurity
    0.97
     takut
    0.97
     paura
    0.95
     medo
    0.94
     fearful
    0.93
     fearing
    0.92
    Act Density 0.202%

    No Known Activations